© 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. 97831
    Prev
    Next
    INDEX
    Explanations

    в

    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
    k
    -0.08
    ಂಪ
    -0.07
    ંપ
    -0.07
    ammu
    -0.07
    κυ
    -0.07
    undes
    -0.07
    മ്പ
    -0.07
     kuh
    -0.07
    una
    -0.07
    ver
    -0.07
    POSITIVE LOGITS
    лекатель
    0.11
    едения
    0.11
    ити
    0.10
    ива
    0.10
    ивая
    0.09
    едение
    0.09
    ивают
    0.09
    ивает
    0.09
    樂
    0.08
    ите
    0.08
    Activations Density 0.001%

    No Known Activations