© 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. 47267
    Prev
    Next
    INDEX
    Explanations

    Raj

    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
    -0.09
     spray
    -0.09
    Spr
    -0.09
    ，也是
    -0.08
     μουσ
    -0.08
     escucha
    -0.07
    Cont
    -0.07
     plasm
    -0.07
     hinges
    -0.07
    $(
    -0.07
    POSITIVE LOGITS
     인해
    0.13
     ontstaat
    0.10
     добиться
    0.10
     얻
    0.09
    获得
    0.09
     પ્રાપ્ત
    0.08
    써
    0.08
    	height
    0.08
     height
    0.08
     logra
    0.08
    Activations Density 0.150%
    No Known Activations