© 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. 69943
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     vingers
    -0.09
     lanç
    -0.08
     biz
    -0.07
    Biz
    -0.07
     lançamento
    -0.07
     lance
    -0.07
     decis
    -0.07
     diss
    -0.07
     pertin
    -0.07
     Dennis
    -0.07
    POSITIVE LOGITS
    һа
    0.11
    һә
    0.09
    һәт
    0.09
    @Many
    0.08
    андид
    0.08
    ுச்
    0.08
    าห์
    0.08
     РФ
    0.08
    างวัล
    0.08
    һын
    0.08
    Activations Density 0.000%

    No Known Activations