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. 19028
    Prev
    Next
    INDEX
    Explanations

    He

    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
     אדער
    -0.13
     йәки
    -0.13
     אָדער
    -0.13
    の名無しさん
    -0.12
     एउ
    -0.12
    हेको
    -0.12
     atanapi
    -0.12
    benzisa
    -0.12
     utawa
    -0.12
     alebo
    -0.11
    POSITIVE LOGITS
     to
    0.11
     like
    0.11
     so
    0.11
     So
    0.09
    like
    0.09
    So
    0.09
     مثل
    0.09
     $
    0.08
    :
    0.08
    e
    0.08
    Activations Density 0.124%

    No Known Activations