© 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. 24635
    Prev
    Next
    INDEX
    Explanations

    math

    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
     goggles
    -0.08
     gyms
    -0.08
     gust
    -0.08
     sal
    -0.07
     til
    -0.07
     sunlight
    -0.07
    wat
    -0.07
     fronte
    -0.07
     GPS
    -0.07
     sure
    -0.07
    POSITIVE LOGITS
    Oui
    0.08
     Monsieur
    0.08
    ologisch
    0.08
     beschäft
    0.08
     multitude
    0.08
     Idee
    0.08
     ironically
    0.08
    好
    0.08
    754
    0.07
    РА
    0.07
    Activations Density 0.018%

    No Known Activations