© 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. 95843
    Prev
    Next
    INDEX
    Explanations

    Reading books

    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
     munk
    -0.08
     этот
    -0.08
     lachen
    -0.08
     minner
    -0.08
     tuple
    -0.08
    ১৯
    -0.08
     отраж
    -0.08
    ১৪
    -0.08
     pregnancies
    -0.07
     bestätigen
    -0.07
    POSITIVE LOGITS
     lentamente
    0.09
    Apps
    0.08
     Apps
    0.08
     steadily
    0.08
     leisurely
    0.08
     reputable
    0.07
    .fore
    0.07
    充分
    0.07
     news
    0.07
    Pages
    0.07
    Activations Density 0.024%

    No Known Activations