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. 97104
    Prev
    Next
    INDEX
    Explanations

    say "ICAL"

    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
     최초
    -0.09
     REM
    -0.08
     einer
    -0.07
     allegedly
    -0.07
     naï
    -0.07
    мад
    -0.07
    ার
    -0.07
     marzo
    -0.07
    -м
    -0.07
    呵
    -0.07
    POSITIVE LOGITS
    ICAL
    0.10
    ിക്കല്
    0.09
    Graphic
    0.08
    _ind
    0.08
     pool
    0.08
    Throughout
    0.08
    (comp
    0.08
    _pool
    0.08
    pool
    0.08
    _sp
    0.08
    Activations Density 0.001%

    No Known Activations