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. 58966
    Prev
    Next
    INDEX
    Explanations

    终

    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
     outright
    -0.08
    jenige
    -0.08
     Gegend
    -0.08
     dommages
    -0.08
     그냥
    -0.07
     falsely
    -0.07
    endif
    -0.07
     cud
    -0.07
     hyst
    -0.07
     ставок
    -0.07
    POSITIVE LOGITS
    领先
    0.09
    鲜
    0.09
     протяжении
    0.08
    保持
    0.08
     pace
    0.08
     atento
    0.08
     freshness
    0.08
    varande
    0.08
    低
    0.08
    贯
    0.08
    Activations Density 0.006%

    No Known Activations