© 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. 78422
    Prev
    Next
    INDEX
    Explanations

    Francis

    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
     коллектив
    -0.08
    .hy
    -0.08
     క్ర
    -0.08
     ಕ್ರ
    -0.08
     Hybrid
    -0.07
    =edge
    -0.07
     рады
    -0.07
     henni
    -0.07
     lì
    -0.07
     మె
    -0.07
    POSITIVE LOGITS
     तुम्ह
    0.08
     beloved
    0.08
     memories
    0.08
    utzt
    0.07
    iliki
    0.07
    友情
    0.07
     planting
    0.07
     apres
    0.07
    容量
    0.07
     Küche
    0.07
    Activations Density 0.001%

    No Known Activations