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. 76537
    Prev
    Next
    INDEX
    Explanations

    classification

    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
    umas
    -0.08
    HOST
    -0.08
     Reciprocity
    -0.08
     reforms
    -0.08
     Printing
    -0.08
     ial
    -0.08
    Printing
    -0.08
     unmet
    -0.08
    願
    -0.08
    cei
    -0.08
    POSITIVE LOGITS
    分類
    0.18
    分类
    0.17
     classification
    0.17
     classify
    0.16
     classifications
    0.16
     Classification
    0.15
     分类
    0.15
    Classification
    0.15
    classification
    0.15
     класси
    0.14
    Activations Density 0.017%

    No Known Activations