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. 15-RESID-POST-AA
    6. 19322
    Prev
    Next
    INDEX
    Explanations

    say 's

    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
     abar
    -0.11
     obwohl
    -0.10
     jeder
    -0.10
     хотя
    -0.10
     einzelnen
    -0.09
     обязательно
    -0.09
     исключительно
    -0.09
     sammeln
    -0.09
     Obwohl
    -0.09
     disadv
    -0.09
    POSITIVE LOGITS
    's
    0.13
    ’s
    0.11
     theorem
    0.10
     University's
    0.10
    的方法
    0.09
    -style
    0.09
     の
    0.09
     的
    0.09
    님의
    0.09
     and
    0.09
    Activations Density 0.034%

    No Known Activations