© 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. 3-RESID-POST-AA
    11. 1395
    Prev
    Next
    INDEX
    Explanations

    York

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Haj
    -0.07
    culation
    -0.07
    瞬
    -0.07
    出来
    -0.07
    黄金
    -0.07
    テ
    -0.07
     لن
    -0.07
     freely
    -0.07
    uera
    -0.07
     Goldman
    -0.07
    POSITIVE LOGITS
     Pan
    0.08
     moj
    0.07
     absol
    0.07
     Kun
    0.07
     �
    0.07
     coi
    0.07
    tia
    0.07
     Kent
    0.07
     patas
    0.07
     cip
    0.07
    Activations Density 0.003%

    No Known Activations