Back to skills
SkillHub ClubShip Full StackFull Stack

sparse-autoencoder-training

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Packaged view

This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.

Stars
8,993
Hot score
99
Updated
March 20, 2026
Overall rating
C4.5
Composite score
4.5
Best-practice grade
B75.6

Install command

npx @skill-hub/cli install nousresearch-hermes-agent-saelens

Repository

NousResearch/hermes-agent

Skill path: skills/mlops/evaluation/saelens

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Open repository

Best for

Primary workflow: Ship Full Stack.

Technical facets: Full Stack.

Target audience: Development teams looking for install-ready agent workflows..

License: Unknown.

Original source

Catalog source: SkillHub Club.

Repository owner: NousResearch.

This is still a mirrored public skill entry. Review the repository before installing into production workflows.

What it helps with

  • Install sparse-autoencoder-training into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
  • Review https://github.com/NousResearch/hermes-agent before adding sparse-autoencoder-training to shared team environments
  • Use sparse-autoencoder-training for development workflows

Works across

Claude CodeCodex CLIGemini CLIOpenCode

Favorites: 0.

Sub-skills: 0.

Aggregator: No.