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. 109629
    Prev
    Next
    INDEX
    Explanations

    making choices in math

    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
    tag
    -0.08
    ODES
    -0.08
     weakness
    -0.08
     зависит
    -0.08
    iyan
    -0.08
    itchie
    -0.07
    their
    -0.07
    odes
    -0.07
    LOVE
    -0.07
     ಪ್ರ
    -0.07
    POSITIVE LOGITS
     simpler
    0.09
     slate
    0.08
     gerust
    0.08
     confidently
    0.08
     స
    0.08
     conveniently
    0.08
     Rok
    0.08
     instead
    0.08
     bequem
    0.08
     مستقیم
    0.07
    Activations Density 0.023%

    No Known Activations