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. 61031
    Prev
    Next
    INDEX
    Explanations

    IT, software, technical documentation

    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
    ,例如
    -0.08
    。例如
    -0.08
     propag
    -0.07
     ста
    -0.07
    важ
    -0.07
    	
    -0.07
     tais
    -0.07
    (
    -0.07
    、
    -0.07
    固
    -0.07
    POSITIVE LOGITS
     Continued
    0.10
    continued
    0.08
    Rx
    0.08
    !)↵↵
    0.08
     Dangerous
    0.08
     animation
    0.08
     Movimiento
    0.07
    Vegas
    0.07
    Wan
    0.07
    Missing
    0.07
    Activations Density 0.192%

    No Known Activations