© 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. 102353
    Prev
    Next
    INDEX
    Explanations

    File paths with `│`

    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
     საკმაოდ
    -0.09
     miliyoni
    -0.09
    იძ
    -0.09
     llawer
    -0.09
     "");
↵
    -0.09
     shumë
    -0.09
     ħafna
    -0.08
     anpil
    -0.08
     Ondanks
    -0.08
    ופו
    -0.08
    POSITIVE LOGITS
    │
    0.10
     útiles
    0.09
    #↵
    0.09
     archivos
    0.09
    |↵
    0.09
     │
    0.09
     Dateien
    0.09
    	files
    0.09
     files
    0.08
     folder
    0.08
    Activations Density 0.003%

    No Known Activations