sae-lookup

sae-lookup is a skill for Claude Code, Codex from OpenInterpretability/openinterp-mcp. It costs 38 tokens per session (530 once invoked), scanned A, original, no licence file.

A tool for breaking down a captured neural-network activation into its most prominent sparse-autoencoder features and showing human-readable names for those features.

In plain words
What is it for?
It is for analysing model activations and identifying the concepts represented by the strongest sparse-autoencoder features.
Why use it?
It helps connect an internal vector from a language model's residual stream to concepts that a person can inspect.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/openinterpretability/openinterp-mcp/sae-lookup
Any agent
npx skills add OpenInterpretability/openinterp-mcp --skill sae-lookup
Clone the repo
git clone --depth 1 https://github.com/OpenInterpretability/openinterp-mcp

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 sae-lookup

README.md
[![agentmods](https://agentmods.dev/badge/skills/openinterpretability/openinterp-mcp/sae-lookup.svg)](https://agentmods.dev/skills/openinterpretability/openinterp-mcp/sae-lookup)
Your own site
<a href="https://agentmods.dev/skills/openinterpretability/openinterp-mcp/sae-lookup"><img src="https://agentmods.dev/badge/skills/openinterpretability/openinterp-mcp/sae-lookup.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 530 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00038 $0.00530
Opus 5 $0.00019 $0.00265
Sonnet 5 $0.00008 $0.00106
Haiku 4.5 $0.00004 $0.00053

Measured 4d ago against content hash 7133471d6c28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

sae-lookup 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 4d 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/sae-lookup/SKILL.md · 46 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. 4d ago First seen · 46 lines · 38 tokens per session scan A 7133471d6c28

Subscribe to this mod's changes

sae-lookup is a skill published in the GitHub repository OpenInterpretability/openinterp-mcp (0 stars, last pushed 2mo ago), with no licence file. It adds 38 tokens to every session and 530 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

torchdrug

Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.

K-Dense-AI/scientific-agent-skills · 61 tokens

arboreto

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…

K-Dense-AI/scientific-agent-skills · 66 tokens

deepspot-m

Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…

K-Dense-AI/scientific-agent-skills · 80 tokens

pyhealth

Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…

K-Dense-AI/scientific-agent-skills · 216 tokens

pick-a-pii-model

Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.

maziyarpanahi/openmed · 64 tokens

esm

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…

synthetic-sciences/openscience · 86 tokens