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. 61022
    Prev
    Next
    INDEX
    Explanations

    Math equations

    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
     Subs
    -0.08
    真人
    -0.08
     кой
    -0.08
     Franchise
    -0.08
    ेस
    -0.08
    摄影
    -0.07
     cams
    -0.07
     yüks
    -0.07
    PERTIES
    -0.07
     supérieure
    -0.07
    POSITIVE LOGITS
     ситуации
    0.09
    .sign
    0.08
     zéro
    0.08
    ungee
    0.08
     séparation
    0.08
    }px
    0.08
    .quantity
    0.08
    ause
    0.08
     независимо
    0.08
     سواء
    0.08
    Activations Density 0.070%

    No Known Activations