© 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. 110742
    Prev
    Next
    INDEX
    Explanations

    page

    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
    َى
    -0.08
    toi
    -0.07
     போன்ற
    -0.07
     uptake
    -0.07
     Pinn
    -0.07
     Steele
    -0.07
     paf
    -0.07
    aben
    -0.07
    /or
    -0.07
     தொட
    -0.07
    POSITIVE LOGITS
     acomod
    0.08
     unintended
    0.08
    cience
    0.07
     petitions
    0.07
    主体
    0.07
     unint
    0.07
    uits
    0.07
     убед
    0.07
     prob
    0.07
    forcing
    0.07
    Activations Density 0.031%

    No Known Activations