© 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 EvalsExportsinterp-engineNEWAPI 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. 110268
    Prev
    Next
    INDEX
    Explanations

    й

    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
     gây
    -0.08
     femme
    -0.08
    edo
    -0.08
     aged
    -0.08
     Economist
    -0.08
    不是
    -0.08
    ED
    -0.08
     ощ
    -0.07
     gazet
    -0.07
    esi
    -0.07
    POSITIVE LOGITS
     jurisdiction
    0.08
     possession
    0.08
     branch
    0.08
    общ
    0.08
    нікаў
    0.08
     obrigação
    0.07
    ұ
    0.07
    нии
    0.07
     शाख
    0.07
     branches
    0.07
    Activations Density 0.001%

    No Known Activations