© 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. 69506
    Prev
    Next
    INDEX
    Explanations

    Anatomy/medical

    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
     Thompson
    -0.09
     onderzoek
    -0.08
     Bres
    -0.08
    �江
    -0.08
     Supplements
    -0.08
     manipulated
    -0.08
     Drap
    -0.08
     расслед
    -0.07
     キャ
    -0.07
     фон
    -0.07
    POSITIVE LOGITS
     mile
    0.08
     marble
    0.07
     greið
    0.07
    approved
    0.07
    ware
    0.07
     earthquakes
    0.07
     mandate
    0.07
    ************************
    0.07
     Martha
    0.07
    支付
    0.07
    Activations Density 0.001%

    No Known Activations