© 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. 63249
    Prev
    Next
    INDEX
    Explanations

    thinking

    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
    .degree
    -0.08
    _num
    -0.08
    (|
    -0.08
    [:
    -0.08
    ROI
    -0.08
    _ft
    -0.07
    有效
    -0.07
    ()->
    -0.07
    易
    -0.07
    规划
    -0.07
    POSITIVE LOGITS
    لعاب
    0.09
     спасибо
    0.08
     Words
    0.08
     gratu
    0.08
    āina
    0.08
     !!↵
    0.08
     Duel
    0.08
     ಕಡೆ
    0.08
    ================================================================
    0.07
     Cats
    0.07
    Activations Density 0.013%

    No Known Activations