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

    Neuronpedia

    Jacobian LensNEW
    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. 113239
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    .website
    -0.08
    website
    -0.08
    .heroku
    -0.08
     strony
    -0.07
     gezeigt
    -0.07
     aam
    -0.07
    (summary
    -0.07
    (nd
    -0.07
     vess
    -0.07
     naut
    -0.07
    POSITIVE LOGITS
     shift
    0.07
    ərbaycan
    0.07
    	cfg
    0.07
     abrir
    0.07
    Rick
    0.07
     phố
    0.07
     дуже
    0.07
     זה
    0.07
     定
    0.07
     confusion
    0.07
    Activations Density 0.018%

    No Known Activations