© 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. 70383
    Prev
    Next
    INDEX
    Explanations

    Phar

    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
     машин
    -0.09
     lipid
    -0.08
    nan
    -0.08
     pleas
    -0.08
     ventil
    -0.08
    lip
    -0.08
     antaŭ
    -0.08
     پور
    -0.07
     куз
    -0.07
     oan
    -0.07
    POSITIVE LOGITS
     जुड़े
    0.09
     arrogant
    0.08
    ública
    0.08
     संबंधित
    0.08
     colleague
    0.07
     lớp
    0.07
     "'"
    0.07
    achement
    0.07
     arrogance
    0.07
     शिक्षक
    0.07
    Activations Density 0.002%

    No Known Activations