© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91270
    Prev
    Next
    INDEX
    Explanations

    negative

    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
    kir
    -0.08
     ebooks
    -0.08
    ừng
    -0.07
     excluded
    -0.07
     Kita
    -0.07
    စား
    -0.07
     ом
    -0.07
    တ်
    -0.07
     favorite
    -0.07
     tham
    -0.07
    POSITIVE LOGITS
    -original
    0.11
    (original
    0.10
     oorspronkelijke
    0.10
    original
    0.10
    _original
    0.10
     ursprüng
    0.09
     originale
    0.09
     intact
    0.09
     originele
    0.09
    qualität
    0.09
    Activations Density 0.017%

    No Known Activations