© 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. 7-RESID-POST-AA
    11. 1390
    Prev
    Next
    INDEX
    Explanations

    абар

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    雪
    -0.08
     mst
    -0.08
    み
    -0.08
     ties
    -0.08
     mellitus
    -0.08
     Clayton
    -0.08
     Copp
    -0.08
     Spurs
    -0.08
    χο
    -0.07
    -0.07
    POSITIVE LOGITS
     안내
    0.07
    156
    0.07
    ters
    0.07
     Prepar
    0.07
     контроль
    0.07
     fada
    0.07
     wavelengths
    0.07
     наполн
    0.07
    (te
    0.07
     Broadcasting
    0.07
    Activations Density 0.000%
    No Known Activations