© 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. 23-RESID-POST-AA
    11. 48984
    Prev
    Next
    INDEX
    Explanations

    Соз

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Us
    -0.07
    ':
    -0.07
    웃
    -0.07
    이를
    -0.07
     ```↵
    -0.07
    ुओं
    -0.07
     сказать
    -0.07
    ünft
    -0.07
     usa
    -0.07
    _to
    -0.07
    POSITIVE LOGITS
    дание
    0.28
    дать
    0.21
    даем
    0.20
    дад
    0.20
    даются
    0.19
    дания
    0.18
    дается
    0.17
    да
    0.16
    даи
    0.16
    даны
    0.16
    Activations Density 0.005%

    No Known Activations