© 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. 68595
    Prev
    Next
    INDEX
    Explanations

    Recipes and ingredients

    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
     zufolge
    -0.08
     characterize
    -0.08
     frc
    -0.07
    ilte
    -0.07
     grundleg
    -0.07
    事情
    -0.07
     parade
    -0.07
     שנה
    -0.07
     mitz
    -0.07
    cies
    -0.07
    POSITIVE LOGITS
    adr
    0.07
    изнес
    0.07
    /API
    0.07
    ази
    0.07
     adopts
    0.07
    /sql
    0.07
    /Application
    0.07
    ಆ
    0.07
    /${
    0.07
    _UINT
    0.07
    Activations Density 0.011%

    No Known Activations