© 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. 110766
    Prev
    Next
    INDEX
    Explanations

    style

    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
     મુ
    -0.07
     puiss
    -0.07
     মুক্ত
    -0.07
    _N
    -0.07
    sometimes
    -0.07
    _async
    -0.07
     asynchronous
    -0.07
     spec
    -0.07
     espec
    -0.07
    িখ
    -0.07
    POSITIVE LOGITS
     Arial
    0.09
    Arial
    0.09
     blauw
    0.09
    fonts
    0.09
     Helvetica
    0.08
    .tint
    0.08
    /styles
    0.08
    ouflage
    0.08
     customization
    0.08
     tailoring
    0.08
    Activations Density 0.002%

    No Known Activations