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. 67181
    Prev
    Next
    INDEX
    Explanations

    EV range

    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
    (struct
    -0.08
     Bern
    -0.08
     الصحية
    -0.08
     لتن
    -0.08
     لص
    -0.08
     تدخل
    -0.08
    	pthread
    -0.07
    objective
    -0.07
     strukt
    -0.07
    _verbose
    -0.07
    POSITIVE LOGITS
     kilometer
    0.10
    途中
    0.10
     kilomet
    0.10
     Mileage
    0.10
     маршру
    0.10
     किलो
    0.10
    续
    0.10
     Kilometer
    0.09
     mile
    0.09
     mileage
    0.09
    Activations Density 0.012%

    No Known Activations