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. 11-RESID-POST-AA
    6. 58707
    Prev
    Next
    INDEX
    Explanations

    gut bacteria metabolites

    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
    _CLR
    -0.09
     känna
    -0.08
     decade
    -0.08
    ேய
    -0.08
    lič
    -0.08
    鹏
    -0.08
     amistad
    -0.07
    Wild
    -0.07
     verlie
    -0.07
     daban
    -0.07
    POSITIVE LOGITS
    -producing
    0.08
    utr
    0.08
     producers
    0.08
    important
    0.07
    -indent
    0.07
     sağlay
    0.07
     Mato
    0.07
     ಉತ್ಪ
    0.07
     ಅಧ
    0.07
     itr
    0.07
    Activations Density 0.000%

    No Known Activations