© 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. 70266
    Prev
    Next
    INDEX
    Explanations

    most

    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
    /Public
    -0.09
     Sedan
    -0.08
     Span
    -0.08
     Exterior
    -0.07
     Romano
    -0.07
    marine
    -0.07
    本金
    -0.07
    (Pro
    -0.07
     mú
    -0.07
    RP
    -0.07
    POSITIVE LOGITS
     pointed
    0.08
     emocionante
    0.08
     ambitious
    0.08
     recentes
    0.08
     accurate
    0.08
     allá
    0.07
     വലിയ
    0.07
     complimentary
    0.07
     economical
    0.07
     큰
    0.07
    Activations Density 0.046%

    No Known Activations