© 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. 78462
    Prev
    Next
    INDEX
    Explanations

    another

    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
     одновременно
    -0.09
     faveur
    -0.08
     Staffing
    -0.08
    	card
    -0.08
     maestros
    -0.08
     Staff
    -0.08
    _OC
    -0.08
    nergies
    -0.08
    uelo
    -0.08
    (Search
    -0.08
    POSITIVE LOGITS
    [state
    0.09
     NST
    0.08
    [position
    0.07
     vie
    0.07
    'impression
    0.07
    旅行
    0.07
    只
    0.07
     travel
    0.07
    Hybrid
    0.07
    HTTPRequest
    0.07
    Activations Density 0.003%

    No Known Activations