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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 29833
    Prev
    Next
    INDEX
    Explanations

    tell

    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
     Trab
    -0.08
    内幕
    -0.08
     mantenimiento
    -0.08
     Havana
    -0.08
     Cambridge
    -0.08
    ,加
    -0.07
    ván
    -0.07
     katika
    -0.07
     vagas
    -0.07
     flashy
    -0.07
    POSITIVE LOGITS
    prime
    0.08
    -w
    0.08
    onga
    0.07
    'article
    0.07
     character
    0.07
     Wann
    0.07
     кон
    0.07
     lift
    0.07
    油
    0.07
    _wire
    0.07
    Activations Density 0.070%

    No Known Activations