© 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. 69827
    Prev
    Next
    INDEX
    Explanations

    dashes

    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
     ప
    -0.08
     lungo
    -0.07
     diseng
    -0.07
     uno
    -0.07
     reluctant
    -0.07
     ألف
    -0.07
     sosp
    -0.07
     perd
    -0.07
     ஒன்று
    -0.07
    培
    -0.07
    POSITIVE LOGITS
     Oceans
    0.08
     zahlen
    0.08
     IR
    0.08
     Calling
    0.07
    occi
    0.07
     ator
    0.07
    .Logging
    0.07
     لوگوں
    0.07
     purse
    0.07
     Nerd
    0.07
    Activations Density 0.009%

    No Known Activations