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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70371
    Prev
    Next
    INDEX
    Explanations

    .el

    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
    Gee
    -0.09
     ngon
    -0.09
     재미
    -0.09
    影音
    -0.08
    (plugin
    -0.08
     qaar
    -0.08
     spool
    -0.08
     Tammy
    -0.08
     toner
    -0.07
     geno
    -0.07
    POSITIVE LOGITS
    _prediction
    0.08
    .pred
    0.07
    ும்ப
    0.07
     दूसरी
    0.07
    _predictions
    0.07
     maximal
    0.07
     vigorously
    0.07
    prediction
    0.07
    ________________
    0.07
    ________
    0.07
    Activations Density 0.000%

    No Known Activations