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. 58496
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ுப்
    -0.09
    енні
    -0.08
    ended
    -0.07
    ിട
    -0.07
    ுச்
    -0.07
    മ്പ
    -0.07
     binnen
    -0.07
     conveying
    -0.07
     Advisors
    -0.07
     ആഭ
    -0.07
    POSITIVE LOGITS
    142
    0.08
    392
    0.08
    trim
    0.08
    Trim
    0.08
     indeed
    0.08
     trim
    0.08
    Ur
    0.08
    352
    0.08
    273
    0.08
     Trim
    0.08
    Activations Density 0.030%

    No Known Activations