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. 46721
    Prev
    Next
    INDEX
    Explanations

    statistics calculations

    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
     incess
    -0.10
     produtividade
    -0.09
     expressing
    -0.09
     Chil
    -0.09
     برقرار
    -0.08
     Chili
    -0.08
     expenditure
    -0.08
     펼
    -0.08
     expend
    -0.08
    }↵↵↵↵/
    -0.08
    POSITIVE LOGITS
     median
    0.11
    中央値
    0.11
    median
    0.10
     percentile
    0.10
    Median
    0.10
     Median
    0.09
     ভোট
    0.08
     elected
    0.08
     votes
    0.08
     floor
    0.08
    Activations Density 0.022%

    No Known Activations