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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64391
    Prev
    Next
    INDEX
    Explanations

    file paths and code

    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
     careg
    -0.09
     childcare
    -0.08
     dov
    -0.07
    DSM
    -0.07
     marang
    -0.07
     गु
    -0.07
    ==='
    -0.07
    完善
    -0.07
     jump
    -0.07
     Jacket
    -0.07
    POSITIVE LOGITS
    .with
    0.09
    .vector
    0.09
     vector
    0.09
    .to
    0.08
    vector
    0.08
    .duration
    0.08
    /by
    0.08
    .query
    0.08
    stone
    0.08
     Vector
    0.08
    Activations Density 0.032%

    No Known Activations