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. 87
    Prev
    Next
    INDEX
    Explanations

    software actions

    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
    ختلف
    -0.09
     নানা
    -0.09
     quase
    -0.09
    ’ailleurs
    -0.09
    ומים
    -0.09
     nearly
    -0.09
     বিভিন্ন
    -0.09
     почти
    -0.08
     gleicher
    -0.08
     akár
    -0.08
    POSITIVE LOGITS
     with
    0.08
    fld
    0.08
     puis
    0.08
     pearl
    0.07
     followed
    0.07
     합니다
    0.07
     ←
    0.07
     or
    0.07
     to
    0.07
    eed
    0.07
    Activations Density 0.064%

    No Known Activations