© 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. 99605
    Prev
    Next
    INDEX
    Explanations

    surely

    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
     маз
    -0.08
     chúng
    -0.08
     Ю
    -0.08
     D
    -0.08
     мы
    -0.08
     UTF
    -0.07
     Anc
    -0.07
    Ю
    -0.07
     нагрузки
    -0.07
     «
    -0.07
    POSITIVE LOGITS
    ವರಿಗೆ
    0.09
    reath
    0.08
    ವರ
    0.07
    一次
    0.07
    nú
    0.07
     alebo
    0.07
     emocion
    0.07
    .navigate
    0.07
    leh
    0.07
    socket
    0.07
    Activations Density 0.491%

    No Known Activations