© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47130
    Prev
    Next
    INDEX
    Explanations

    Automated code formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     semiconductor
    -0.09
     conducting
    -0.08
     terwijl
    -0.08
     ingenuity
    -0.08
     electromagnetic
    -0.08
    Innovation
    -0.08
     imaginative
    -0.08
    kut
    -0.08
     Rutherford
    -0.08
     �
    -0.08
    POSITIVE LOGITS
    eslint
    0.14
     lint
    0.13
     prettier
    0.13
    -eslint
    0.12
    Lint
    0.12
     eslint
    0.12
    lint
    0.12
     ESL
    0.11
     clang
    0.11
     vscode
    0.11
    Activations Density 0.004%

    No Known Activations