© 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 EvalsExportsAPI 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. 113153
    Prev
    Next
    INDEX
    Explanations

    canonical

    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
    卒
    -0.08
     offspring
    -0.08
    .an
    -0.07
     adjective
    -0.07
     Lieutenant
    -0.07
     centre
    -0.07
     aprovação
    -0.07
     Kenntnisse
    -0.07
     neonatal
    -0.07
     kapit
    -0.07
    POSITIVE LOGITS
    コピー
    0.09
     Pollution
    0.09
     duplicate
    0.09
     duplication
    0.08
     prevents
    0.08
    duplicate
    0.08
     Duplicate
    0.08
     duplicated
    0.08
     Pagination
    0.08
    Duplicate
    0.08
    Activations Density 0.001%

    No Known Activations