© 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. 19-RESID-POST-AA
    11. 19177
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    -0.07
     daarom
    -0.07
     actually
    -0.07
    's
    -0.07
     da
    -0.07
     voet
    -0.07
    ertal
    -0.06
     derfor
    -0.06
     zapr
    -0.06
    n't
    -0.06
    POSITIVE LOGITS
     [...]↵
    0.25
     વગેરે
    0.24
    ,...
    0.24
    ...[
    0.24
     וכו
    0.24
    [...]↵↵
    0.24
     ..."
    0.24
     وغيرها
    0.24
     etc
    0.23
     आदि
    0.23
    Activations Density 0.061%

    No Known Activations