© 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. 3-RESID-POST-AA
    11. 1322
    Prev
    Next
    INDEX
    Explanations

    /s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ಟ
    -0.08
     Федера
    -0.08
    <Api
    -0.07
     Session
    -0.07
    	ans
    -0.07
     Ferro
    -0.07
     Primer
    -0.07
    queles
    -0.07
    णे
    -0.07
     Reli
    -0.07
    POSITIVE LOGITS
     studi
    0.08
    ,col
    0.08
     neglect
    0.07
    functions
    0.07
    ieg
    0.07
    dx
    0.07
     zon
    0.07
     defects
    0.07
     στον
    0.07
     muutt
    0.07
    Activations Density 0.000%

    No Known Activations