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. 46492
    Prev
    Next
    INDEX
    Explanations

    Stephen Curry

    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
    Exports
    -0.08
     Север
    -0.08
     Gep
    -0.07
     Esther
    -0.07
     Raff
    -0.07
    _GAIN
    -0.07
     Infant
    -0.07
     Gow
    -0.07
    (container
    -0.07
    .Container
    -0.07
    POSITIVE LOGITS
     recorr
    0.08
     mucus
    0.08
     streak
    0.08
     dvije
    0.08
     déficit
    0.07
    اته
    0.07
    镇
    0.07
     فريق
    0.07
     tanden
    0.07
    実況
    0.07
    Activations Density 0.003%

    No Known Activations