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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 734
    Prev
    Next
    INDEX
    Explanations

    academics

    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
    344
    -0.08
     круг
    -0.08
    ണി
    -0.08
     eql
    -0.08
    326
    -0.08
    330
    -0.07
     private
    -0.07
     Clan
    -0.07
    凉
    -0.07
     Vibr
    -0.07
    POSITIVE LOGITS
     משרד
    0.08
     Montréal
    0.08
     착
    0.08
    <F
    0.08
     businessman
    0.07
    atah
    0.07
     academics
    0.07
     membre
    0.07
     Cran
    0.07
    wj
    0.07
    Activations Density 0.023%

    No Known Activations