© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 77918
    Prev
    Next
    INDEX
    Explanations

    Nouveau

    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
     مصدر
    -0.08
     wahrscheinlich
    -0.08
     vermutlich
    -0.08
     interp
    -0.07
    ouns
    -0.07
     waarschijnlijk
    -0.07
     பட
    -0.07
    Ep
    -0.07
     normen
    -0.07
     qor
    -0.07
    POSITIVE LOGITS
     Ý
    0.09
     cybers
    0.08
    /tab
    0.08
    misc
    0.08
    版
    0.08
     trendy
    0.08
     gladly
    0.07
    pline
    0.07
     railing
    0.07
     downfall
    0.07
    Activations Density 0.002%

    No Known Activations