© 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. 30927
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     will
    -0.08
    Subtitle
    -0.07
     motivate
    -0.07
     @
    -0.07
    Route
    -0.07
    леж
    -0.07
    Message
    -0.07
    Type
    -0.07
     trad
    -0.07
    Name
    -0.07
    POSITIVE LOGITS
    	sum
    0.10
     Sum
    0.10
     బాల
    0.09
    _sum
    0.09
    Sum
    0.09
     sum
    0.09
     Παν
    0.09
     fotografías
    0.08
     ಬಾಲ
    0.08
    owing
    0.08
    Activations Density 0.039%

    No Known Activations