© 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. 63148
    Prev
    Next
    INDEX
    Explanations

    Geometry, Russian, and numbers

    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
     harvest
    -0.08
    সং
    -0.07
    指导
    -0.07
    巧
    -0.07
     consisted
    -0.07
     sidste
    -0.07
     descriptions
    -0.07
     সং
    -0.07
     references
    -0.07
    —and
    -0.06
    POSITIVE LOGITS
    ?,?,?,?,
    0.12
    ;amp
    0.09
     Parcelable
    0.08
    فين
    0.08
    ,etc
    0.08
    」、「
    0.08
    》、《
    0.08
     gos
    0.08
     Similarly
    0.08
    (){
    0.08
    Activations Density 0.212%

    No Known Activations