© 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. 91516
    Prev
    Next
    INDEX
    Explanations

    kg

    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
     evidenced
    -0.10
     considerate
    -0.09
    ensya
    -0.08
     evidently
    -0.08
     بالر
    -0.07
     ಇರುವ
    -0.07
     موجود
    -0.07
     aiding
    -0.07
     لدي
    -0.07
     lowered
    -0.07
    POSITIVE LOGITS
    #,
    0.07
     /*↵
    0.07
    0.07
    #if
    0.07
     Burt
    0.07
    рощ
    0.07
     Silver
    0.07
     Rap
    0.07
     보면
    0.07
     sht
    0.07
    Activations Density 0.002%
    No Known Activations