Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 65634
    Prev
    Next
    INDEX
    Explanations

    Articles

    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
    _diag
    -0.08
    Diag
    -0.08
    (Matrix
    -0.08
     technicians
    -0.07
     diag
    -0.07
    (set
    -0.07
    挥
    -0.07
    Personnel
    -0.07
    (EXIT
    -0.07
    diag
    -0.07
    POSITIVE LOGITS
     curated
    0.11
     discoveries
    0.11
     ссылки
    0.10
     références
    0.10
     समाचार
    0.10
    сыл
    0.09
     referências
    0.09
     Discover
    0.09
    references
    0.09
     distribuição
    0.09
    Activations Density 0.038%

    No Known Activations