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

    Neuronpedia

    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. 79400
    Prev
    Next
    INDEX
    Explanations

    Workspace software

    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
     traveled
    -0.08
    aptation
    -0.08
    tong
    -0.08
     იტ
    -0.07
     jig
    -0.07
     applique
    -0.07
     আটক
    -0.07
     Deutschlands
    -0.07
    .PARAM
    -0.07
     lodged
    -0.07
    POSITIVE LOGITS
     Gmail
    0.09
     సభ్య
    0.09
     корпоратив
    0.08
     wellness
    0.08
     Workspace
    0.08
    なら
    0.08
     cuentas
    0.08
     civ
    0.07
     брен
    0.07
    Members
    0.07
    Activations Density 0.004%

    No Known Activations