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. 30559
    Prev
    Next
    INDEX
    Explanations

    Math exponents

    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
     цит
    -0.09
     quoting
    -0.08
    _excerpt
    -0.07
     Obamacare
    -0.07
     Premier
    -0.07
    _DISABLE
    -0.07
     خطاب
    -0.07
    .Disable
    -0.07
     उद्ध
    -0.07
     readership
    -0.07
    POSITIVE LOGITS
    Pairs
    0.09
    Odd
    0.08
     okaz
    0.08
     અસ
    0.08
    oddi
    0.08
    niają
    0.08
    ífico
    0.07
    _pairs
    0.07
     odd
    0.07
     השל
    0.07
    Activations Density 0.018%

    No Known Activations