© 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. 15-RESID-POST-AA
    11. 16303
    Prev
    Next
    INDEX
    Explanations

    for/to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     그리고
    -0.08
     어떻게
    -0.08
     внимательно
    -0.07
     또한
    -0.07
    chappen
    -0.07
     нь
    -0.07
    pheres
    -0.07
    orientation
    -0.07
    ücht
    -0.07
    ackle
    -0.07
    POSITIVE LOGITS
    ，否则
    0.14
    才能
    0.14
    否则
    0.10
     meaningful
    0.10
     jotta
    0.09
     ताकि
    0.09
    ?)↵
    0.09
     чтобы
    0.09
     જેથી
    0.09
     যাতে
    0.09
    Activations Density 0.015%

    No Known Activations