© 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. 71156
    Prev
    Next
    INDEX
    Explanations

    cash

    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
     Helper
    -0.08
     نجاح
    -0.07
    _backend
    -0.07
    gy
    -0.07
    ertype
    -0.07
    ardware
    -0.07
     ن
    -0.07
    claimer
    -0.07
     selle
    -0.07
    gende
    -0.06
    POSITIVE LOGITS
     процентов
    0.09
     Sonn
    0.09
    备用
    0.09
     Emails
    0.08
     necesidades
    0.08
     מדי
    0.08
    Remain
    0.08
    /year
    0.08
     plain
    0.08
     regularmente
    0.08
    Activations Density 0.006%

    No Known Activations