Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43258
    Prev
    Next
    INDEX
    Explanations

    debates

    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
     realización
    -0.09
    .stats
    -0.08
     barcode
    -0.08
     pictures
    -0.08
     mushrooms
    -0.07
     remembering
    -0.07
    ாப்ப
    -0.07
    Imgs
    -0.07
    .IDENTITY
    -0.07
     creating
    -0.07
    POSITIVE LOGITS
    (topic
    0.11
     debating
    0.10
     Debate
    0.10
     Topic
    0.10
     opposing
    0.09
    topic
    0.09
     বিত
    0.09
    �
    0.09
     topic
    0.09
    /topic
    0.09
    Activations Density 0.016%

    No Known Activations