© 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. 70995
    Prev
    Next
    INDEX
    Explanations

    displaying information

    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
    alent
    -0.09
     Accurate
    -0.08
     раск
    -0.08
     пора
    -0.08
    ಾಂಕ
    -0.07
     جيئن
    -0.07
     Industria
    -0.07
    ورة
    -0.07
    okon
    -0.07
     completo
    -0.07
    POSITIVE LOGITS
     illusions
    0.08
     dependencies
    0.08
    (points
    0.08
     cro
    0.08
     ~
    0.07
     deps
    0.07
     reviews
    0.07
     slides
    0.07
    reviews
    0.07
     ആശ
    0.07
    Activations Density 0.021%

    No Known Activations