© 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. 78308
    Prev
    Next
    INDEX
    Explanations

    one

    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
     fad
    -0.08
     Fence
    -0.08
    ane
    -0.08
    cmp
    -0.08
    fax
    -0.07
    Fence
    -0.07
     faixa
    -0.07
    яць
    -0.07
    Forest
    -0.07
     Moo
    -0.07
    POSITIVE LOGITS
     黃
    0.08
    ographies
    0.07
     podrás
    0.07
    الث
    0.07
     geleerd
    0.07
     Libertadores
    0.07
     podrán
    0.07
     αυτές
    0.07
    Batis
    0.07
    LIB
    0.07
    Activations Density 0.001%

    No Known Activations