© 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. 44665
    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
     annually
    -0.07
     tender
    -0.07
    �
    -0.07
    这些
    -0.07
    -0.07
    [R
    -0.07
    様
    -0.07
     Nep
    -0.07
     insgesamt
    -0.07
     یې
    -0.06
    POSITIVE LOGITS
    achuun
    0.08
    -options
    0.08
     byť
    0.08
     Angie
    0.08
    endors
    0.08
    -envelope
    0.08
    locator
    0.08
     trackers
    0.07
    ///<
    0.07
     Magnum
    0.07
    Activations Density 0.018%
    No Known Activations