© 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. 23-RESID-POST-AA
    11. 6210
    Prev
    Next
    INDEX
    Explanations

    opp

    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
    osite
    -0.09
     Subs
    -0.08
     ជ
    -0.08
     sva
    -0.08
    impin
    -0.08
    GED
    -0.08
    梦想
    -0.08
     воб
    -0.08
     consé
    -0.08
    Vars
    -0.08
    POSITIVE LOGITS
    oses
    0.10
    -P
    0.09
    ress
    0.09
    posed
    0.08
    .P
    0.08
    не
    0.08
     px
    0.08
     ppt
    0.08
    ressing
    0.08
    xygen
    0.07
    Activations Density 0.000%

    No Known Activations