© 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. 25267
    Prev
    Next
    INDEX
    Explanations

    hedging language

    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
    Hands
    -0.09
    awanda
    -0.08
     arre
    -0.08
    Working
    -0.08
    Gebruik
    -0.08
    insk
    -0.07
     daardoor
    -0.07
    Util
    -0.07
    Longitude
    -0.07
    /install
    -0.07
    POSITIVE LOGITS
     damn
    0.10
     Exception
    0.09
     Depends
    0.08
     menurut
    0.08
    願
    0.08
     Episode
    0.08
     Tag
    0.08
     Himself
    0.08
    偷偷
    0.08
     Actually
    0.08
    Activations Density 0.095%

    No Known Activations