Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76056
    Prev
    Next
    INDEX
    Explanations

    Chinese language

    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
     മാറ
    -0.08
    оритет
    -0.08
    posti
    -0.08
    .";↵↵
    -0.08
     pò
    -0.07
     शीर्ष
    -0.07
     બદલ
    -0.07
    .',↵
    -0.07
     ۔
    -0.07
     whoever
    -0.07
    POSITIVE LOGITS
     comedy
    0.08
     va
    0.08
     Polyester
    0.07
     Hello
    0.07
     Toast
    0.07
     expenditures
    0.07
     Zv
    0.07
    Sprite
    0.07
    Hello
    0.07
    ъл
    0.07
    Activations Density 0.000%

    No Known Activations