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. 119272
    Prev
    Next
    INDEX
    Explanations

    math symbols

    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
     Sent
    -0.08
    agent
    -0.08
     aesthetically
    -0.08
    .sent
    -0.08
    Sent
    -0.08
    (sent
    -0.08
     така
    -0.08
    sent
    -0.08
    entity
    -0.07
    :block
    -0.07
    POSITIVE LOGITS
     numerator
    0.11
     scaled
    0.09
     normalized
    0.09
    )/
    0.09
    ()/
    0.09
    )/(
    0.09
    scaled
    0.09
    }/
    0.08
    ']/
    0.08
    Scaled
    0.08
    Activations Density 0.182%

    No Known Activations