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. 11-RESID-POST-AA
    6. 43895
    Prev
    Next
    INDEX
    Explanations

    )

    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
    етра
    -0.08
    ազ
    -0.08
     They'll
    -0.08
     �
    -0.08
     consideradas
    -0.07
     poised
    -0.07
    ავლ
    -0.07
    ాత్ర
    -0.07
     si
    -0.07
     Сдел
    -0.07
    POSITIVE LOGITS
     readers
    0.09
    0.07
     کمک
    0.07
    Results
    0.07
     results
    0.07
    Readers
    0.07
    _ALT
    0.07
    nbsp
    0.07
    
    
    ↵
    0.07
     عنوان
    0.07
    Activations Density 0.001%

    No Known Activations