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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 114
    Prev
    Next
    INDEX
    Explanations

    以

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /API
    -0.10
     επίσης
    -0.10
    muy
    -0.09
    Muy
    -0.09
     आदि
    -0.09
     derejes
    -0.09
     โบนัส
    -0.09
     zeer
    -0.08
     նաև
    -0.08
     ထ
    -0.08
    POSITIVE LOGITS
    ૈ
    0.10
    .
    0.08
     الله
    0.08
    人为
    0.08
    文明
    0.08
     love
    0.08
     بالم
    0.08
     любовь
    0.08
    群众
    0.08
    уман
    0.07
    Activations Density 0.006%

    No Known Activations