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. 19221
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    ividade
    -0.08
     grandfather
    -0.08
     חוש
    -0.08
    gmail
    -0.08
     గుర్త
    -0.08
    [$
    -0.07
    itivity
    -0.07
     gmail
    -0.07
    etti
    -0.07
     среднего
    -0.07
    POSITIVE LOGITS
     उतर
    0.11
    徒歩
    0.11
     boarding
    0.10
     ash
    0.10
     débar
    0.10
    Extraction
    0.10
     extraction
    0.10
    _transfer
    0.09
    岸
    0.09
     detachable
    0.09
    Activations Density 0.029%

    No Known Activations