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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 63432
    Prev
    Next
    INDEX
    Explanations

    istic

    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
     audits
    -0.08
    (pipe
    -0.08
     пти
    -0.08
    olka
    -0.07
    haupt
    -0.07
    Surface
    -0.07
    间
    -0.07
    VA
    -0.07
     Diagnose
    -0.07
     услов
    -0.07
    POSITIVE LOGITS
     dissemination
    0.09
     assimil
    0.09
     twilight
    0.09
     diaspora
    0.09
     Disse
    0.09
     dissemin
    0.08
     civilization
    0.08
     worldly
    0.08
     kale
    0.08
     dias
    0.08
    Activations Density 0.003%

    No Known Activations