© 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. 99825
    Prev
    Next
    INDEX
    Explanations

    im

    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
     secur
    -0.08
     кой
    -0.08
     Nether
    -0.08
     svojih
    -0.08
     stabile
    -0.08
     sart
    -0.07
     recovered
    -0.07
     paradox
    -0.07
     Closet
    -0.07
     organizer
    -0.07
    POSITIVE LOGITS
    式
    0.07
    印
    0.07
     précéd
    0.07
    ுகளில்
    0.07
    .endswith
    0.07
    elerinde
    0.07
     günst
    0.07
    નમાં
    0.07
    blockquote
    0.07
    ുകളിൽ
    0.07
    Activations Density 0.001%

    No Known Activations