© 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. 111057
    Prev
    Next
    INDEX
    Explanations

    null or zero

    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
    .Sn
    -0.07
     Netflix
    -0.07
     claws
    -0.07
     utmost
    -0.07
     Prior
    -0.07
     regret
    -0.07
    ागत
    -0.07
    neet
    -0.07
     academic
    -0.07
    .builders
    -0.07
    POSITIVE LOGITS
    '][$
    0.08
    认为
    0.08
    -invalid
    0.08
     dodat
    0.08
     reprehenderit
    0.08
     §
    0.08
    :\/\/
    0.08
     plain
    0.08
     Internacional
    0.07
    ':''
    0.07
    Activations Density 0.002%

    No Known Activations