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. 56027
    Prev
    Next
    INDEX
    Explanations

    crossing, passing

    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
    967
    -0.08
     Flame
    -0.07
     Tri
    -0.07
     Edition
    -0.07
     flaw
    -0.07
    776
    -0.07
    064
    -0.07
     Fruits
    -0.07
     tri
    -0.07
    464
    -0.07
    POSITIVE LOGITS
     completely
    0.09
     contiguous
    0.09
     Completely
    0.08
    Iran
    0.08
    Interestingly
    0.08
     completamente
    0.08
    机场
    0.08
     ڇ
    0.08
    istit
    0.07
     الخليج
    0.07
    Activations Density 0.004%

    No Known Activations