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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 41975
    Prev
    Next
    INDEX
    Explanations

    of

    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
    imum
    -0.08
     haber
    -0.08
    という
    -0.08
     hiyo
    -0.08
    ភាព
    -0.07
    тиз
    -0.07
     tlhok
    -0.07
    ាញ
    -0.07
    ման
    -0.07
    нең
    -0.07
    POSITIVE LOGITS
     Erkrank
    0.08
     gymnastics
    0.08
    ummed
    0.07
     typed
    0.07
    omo
    0.07
     olahraga
    0.07
     Volleyball
    0.07
    otta
    0.07
     doenças
    0.07
    Corn
    0.07
    Activations Density 0.000%

    No Known Activations