© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102208
    Prev
    Next
    INDEX
    Explanations

    hyphens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "/"
    -0.09
     Իր
    -0.09
    इर
    -0.09
     ?>"><?
    -0.08
     ?>&
    -0.08
     irritated
    -0.08
    डेट
    -0.08
    	of
    -0.08
     gpointer
    -0.08
     трубы
    -0.08
    POSITIVE LOGITS
    ↵
    0.10
    -
    0.09
     use
    0.09
    ,
    0.08
    ',
    0.08
     (
    0.08
    -all
    0.08
    ;↵
    0.08
    ',↵
    0.07
    -B
    0.07
    Activations Density 0.001%

    No Known Activations