© 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. 54780
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    üşt
    -0.08
    ולט
    -0.08
    ply
    -0.07
     Pune
    -0.07
    companies
    -0.07
     legumes
    -0.07
    nst
    -0.07
     tila
    -0.07
    istič
    -0.07
     piste
    -0.07
    POSITIVE LOGITS
     Nich
    0.09
     =
    0.08
     glands
    0.07
    ောက်
    0.07
    头
    0.07
     erne
    0.07
     cabeza
    0.07
     renouvel
    0.07
     desg
    0.07
     erneut
    0.07
    Activations Density 0.013%

    No Known Activations