sparse-autoencoder-training

sparse-autoencoder-training is a skill for Claude Code, Codex from raphaelmansuy/edgecrab. It costs 58 tokens per session (3,279 once invoked), scanned A, original, no licence file.

Guidance for training and examining sparse autoencoders with SAELens. A sparse autoencoder is a model-analysis method that represents neural-network activity using a small number of active features.

In plain words
What is it for?
Use it to find interpretable features in model activations, investigate superposition, and study whether individual features correspond to distinct concepts.
Why use it?
It helps researchers study what internal patterns a language model has learned, including cases where many concepts share the same network activity.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it to find interpretable features in model activations, investigate superposition, and study whether individual features correspond to distinct concepts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/raphaelmansuy/edgecrab/saelens
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add raphaelmansuy/edgecrab --skill saelens
Clone the repo
git clone --depth 1 https://github.com/raphaelmansuy/edgecrab

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for sparse-autoencoder-training

README.md
[![agentmods](https://agentmods.dev/badge/skills/raphaelmansuy/edgecrab/saelens.svg)](https://agentmods.dev/skills/raphaelmansuy/edgecrab/saelens)
Your own site
<a href="https://agentmods.dev/skills/raphaelmansuy/edgecrab/saelens"><img src="https://agentmods.dev/badge/skills/raphaelmansuy/edgecrab/saelens.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.03279
Opus 5 $0.00029 $0.01639
Sonnet 5 $0.00012 $0.00656
Haiku 4.5 $0.00006 $0.00328

Measured 8d ago against content hash 26b92b40c16d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sparse-autoencoder-training scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/mlops/evaluation/saelens/SKILL.md · 390 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 390 lines · 58 tokens per session scan A 26b92b40c16d

Subscribe to this mod's changes

sparse-autoencoder-training is a skill published in the GitHub repository raphaelmansuy/edgecrab (85 stars, last pushed 1mo ago), with no licence file. It adds 58 tokens to every session and 3,279 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

histolab

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

synthetic-sciences/openscience · 62 tokens

torch-geometric

Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.

synthetic-sciences/openscience · 41 tokens

zarr-python

Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.

synthetic-sciences/openscience · 42 tokens

glycobiology

Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.

synthetic-sciences/openscience · 67 tokens

pyhealth

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC)…

synthetic-sciences/openscience · 109 tokens

deepchem

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…

synthetic-sciences/openscience · 78 tokens