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. 60945
    Prev
    Next
    INDEX
    Explanations

    craft instructions

    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
     generator
    -0.09
    ありがとうございます
    -0.08
    generator
    -0.08
     rewritten
    -0.08
    Skipped
    -0.08
    Exact
    -0.08
    γα
    -0.07
    429
    -0.07
    Thanks
    -0.07
    Generator
    -0.07
    POSITIVE LOGITS
    玻
    0.09
     編
    0.09
     soot
    0.08
    ांत
    0.08
     kiuj
    0.08
     添加
    0.08
     plastics
    0.08
     slit
    0.08
     letan
    0.08
     eventuell
    0.08
    Activations Density 0.031%

    No Known Activations