© 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. 23-RESID-POST-AA
    11. 6676
    Prev
    Next
    INDEX
    Explanations

    Serv

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dragged
    -0.09
     insanların
    -0.08
    kannten
    -0.08
     बड़े
    -0.08
     אנשי
    -0.08
     ανθρώ
    -0.07
    örer
    -0.07
    പ്പെട്ടു
    -0.07
    Ab
    -0.07
    holders
    -0.07
    POSITIVE LOGITS
     servings
    0.09
    es
    0.09
    INGS
    0.09
     noc
    0.08
    0.08
    онад
    0.08
    ьв
    0.08
    制造
    0.08
    ેસ
    0.08
    作用
    0.08
    Activations Density 0.001%
    No Known Activations