© 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. 3-RESID-POST-AA
    11. 13317
    Prev
    Next
    INDEX
    Explanations

    Carthy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     зд
    -0.08
    ↵↵//
    -0.08
     Rudolf
    -0.08
     пару
    -0.08
     paranoid
    -0.07
     Tö
    -0.07
     jitter
    -0.07
    且
    -0.07
    ösen
    -0.07
     Pey
    -0.07
    POSITIVE LOGITS
     વિસ્તાર
    0.08
     Merry
    0.08
    Harvest
    0.08
    Ge
    0.08
     ناش
    0.08
     geograf
    0.08
    Ele
    0.07
    )/(
    0.07
    /store
    0.07
    Norm
    0.07
    Activations Density 0.001%

    No Known Activations