© 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. 114337
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     Depart
    -0.09
     زوج
    -0.08
     Nora
    -0.07
    Depart
    -0.07
     youngest
    -0.07
     gelt
    -0.07
     departures
    -0.07
     socks
    -0.07
     Markle
    -0.07
     NK
    -0.07
    POSITIVE LOGITS
     fruitful
    0.08
     earthquakes
    0.08
    忽
    0.08
     happier
    0.08
    _BLEND
    0.08
    _USED
    0.07
     happiness
    0.07
    ở
    0.07
    绩
    0.07
    ？」↵
    0.07
    Activations Density 0.002%

    No Known Activations