© 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. 231
    Prev
    Next
    INDEX
    Explanations

    尺度

    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
    로나
    -0.08
    chr
    -0.07
     maut
    -0.07
     listrik
    -0.07
     connaît
    -0.07
    antaine
    -0.07
     sponsor
    -0.07
     legislative
    -0.07
    ன்
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     scales
    0.13
     levels
    0.10
    (scale
    0.10
    .scale
    0.10
    Levels
    0.10
    尺度
    0.09
     Levels
    0.09
    	scale
    0.09
     šk
    0.09
    .zoom
    0.09
    Activations Density 0.005%

    No Known Activations