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. 78568
    Prev
    Next
    INDEX
    Explanations

    因

    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
    Gut
    -0.07
     Gus
    -0.07
    entas
    -0.07
    otech
    -0.07
     Advis
    -0.07
     ruling
    -0.07
    ség
    -0.07
     comple
    -0.07
     الصحي
    -0.07
     methane
    -0.07
    POSITIVE LOGITS
    OOM
    0.08
     circunst
    0.08
     quests
    0.07
     coincid
    0.07
     حفظ
    0.07
     creating
    0.07
     coincidence
    0.07
     adanya
    0.07
     curiosity
    0.07
     ktoś
    0.07
    Activations Density 0.003%

    No Known Activations