© 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. 114329
    Prev
    Next
    INDEX
    Explanations

    4

    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
     malo
    -0.08
     Kendall
    -0.07
    ාල
    -0.07
     slap
    -0.07
     tensión
    -0.07
     Hil
    -0.07
     eleven
    -0.07
    ामी
    -0.07
     بيع
    -0.07
     Clinton
    -0.07
    POSITIVE LOGITS
    гач
    0.08
    িন
    0.08
    ды
    0.08
    ivariate
    0.08
    Validators
    0.08
    Increase
    0.08
    Outbound
    0.07
    202
    0.07
    Decode
    0.07
    ২০২
    0.07
    Activations Density 0.456%

    No Known Activations