© 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. 5463
    Prev
    Next
    INDEX
    Explanations

    I

    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
    дравствуйте
    -0.10
    seudo
    -0.09
    ажно
    -0.09
    こんにちは
    -0.08
    ੧
    -0.08
    seud
    -0.08
    _CC
    -0.08
    _embedding
    -0.07
     نشر
    -0.07
     typeof
    -0.07
    POSITIVE LOGITS
    KEA
    0.15
    kea
    0.15
    stanbul
    0.13
    celand
    0.13
    gu
    0.11
    vy
    0.10
    onic
    0.10
    phone
    0.09
    ber
    0.09
     Can
    0.09
    Activations Density 0.005%

    No Known Activations