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. 19256
    Prev
    Next
    INDEX
    Explanations

    %

    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
     jud
    -0.08
     Буд
    -0.08
    -0.08
    िङ
    -0.08
    णार
    -0.08
     सुंदर
    -0.08
     *,↵
    -0.07
    :↵↵
    -0.07
     approximate
    -0.07
     uvijek
    -0.07
    POSITIVE LOGITS
     grâce
    0.12
     graças
    0.11
     gracias
    0.11
     dankzij
    0.11
     благодаря
    0.10
     grazie
    0.10
     thanks
    0.10
     doordat
    0.10
     بالإضافة
    0.09
     Furthermore
    0.09
    Activations Density 0.018%

    No Known Activations