© 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. 11-RESID-POST-AA
    11. 78124
    Prev
    Next
    INDEX
    Explanations

    differences in code

    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
     ooit
    -0.07
    863
    -0.07
     vracht
    -0.07
     happier
    -0.07
    SRC
    -0.07
    .Deep
    -0.07
     régulièrement
    -0.07
     Fundament
    -0.07
     essays
    -0.07
     Deep
    -0.07
    POSITIVE LOGITS
     rie
    0.09
    oben
    0.08
     asci
    0.08
     itd
    0.07
    нан
    0.07
    itel
    0.07
    πάν
    0.07
    사항
    0.07
     tú
    0.07
     specifies
    0.07
    Activations Density 0.024%

    No Known Activations