© 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. 91540
    Prev
    Next
    INDEX
    Explanations

    data backup

    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
     endorsement
    -0.08
    历史
    -0.08
    macen
    -0.08
    -0.08
     মনে
    -0.08
     Дума
    -0.07
    blah
    -0.07
     unap
    -0.07
     نظر
    -0.07
    ỏa
    -0.07
    POSITIVE LOGITS
    収
    0.09
    く
    0.09
    Lap
    0.08
     Festa
    0.08
     kamer
    0.08
     photographing
    0.08
     Lap
    0.08
     peacefully
    0.08
     bd
    0.08
     détour
    0.07
    Activations Density 0.003%
    No Known Activations