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. 43974
    Prev
    Next
    INDEX
    Explanations

    punch

    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
     Pb
    -0.07
    Citation
    -0.07
     incent
    -0.07
    Stamp
    -0.07
     przy
    -0.07
    Unknown
    -0.07
    Movie
    -0.07
    Pb
    -0.07
    Snapshot
    -0.07
     aute
    -0.07
    POSITIVE LOGITS
     इत
    0.08
    _BOUND
    0.08
    (fe
    0.07
    霸
    0.07
     אחד
    0.07
    asseur
    0.07
     dreams
    0.07
     Ragnar
    0.07
    ांनी
    0.07
     Bauer
    0.07
    Activations Density 0.006%

    No Known Activations