© 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. 108601
    Prev
    Next
    INDEX
    Explanations

    literature

    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
    'huile
    -0.09
     الحرارة
    -0.08
     taxis
    -0.08
     virksomheder
    -0.08
     temperaturas
    -0.08
     Michelin
    -0.08
     estás
    -0.08
     состояния
    -0.08
     continents
    -0.07
    acotta
    -0.07
    POSITIVE LOGITS
    文学
    0.10
    教材
    0.10
    作品
    0.09
     ಸಾಹಿತ್ಯ
    0.09
     repertoire
    0.09
     curriculum
    0.09
     literary
    0.09
     ادب
    0.08
    -liter
    0.08
    一本
    0.08
    Activations Density 0.000%

    No Known Activations