Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 106341
    Prev
    Next
    INDEX
    Explanations

    digital mobile interactive technologies

    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
    coeff
    -0.10
    _coeff
    -0.09
     coefficients
    -0.08
     recursively
    -0.08
     gordura
    -0.08
    Coef
    -0.08
    Coefficient
    -0.08
     obes
    -0.08
    (coeff
    -0.08
    Coeff
    -0.08
    POSITIVE LOGITS
     kios
    0.13
     concierge
    0.12
     안내
    0.11
     Concierge
    0.11
     kiosk
    0.11
     অতিথ
    0.10
     personalized
    0.10
    游客
    0.10
     RFID
    0.10
     guests
    0.10
    Activations Density 0.021%

    No Known Activations