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. 23-RESID-POST-AA
    6. 98084
    Prev
    Next
    INDEX
    Explanations

    say "312"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clause
    -0.09
     ক্ল
    -0.09
    Cl
    -0.08
     kon
    -0.08
     clone
    -0.08
     Cl
    -0.08
    ptune
    -0.08
     கண்ட
    -0.08
     والتن
    -0.08
     retrospective
    -0.08
    POSITIVE LOGITS
    312
    0.27
    	cal
    0.19
    (cal
    0.19
    _cal
    0.19
    .cal
    0.17
    -cal
    0.17
    Calculator
    0.17
    212
    0.16
    calculator
    0.16
     каль
    0.16
    Activations Density 0.021%

    No Known Activations