© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 50641
    Prev
    Next
    INDEX
    Explanations

    uc

    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
    玩家
    -0.08
     humide
    -0.08
    tect
    -0.08
     深圳
    -0.08
     Lebensmittel
    -0.08
    贵州
    -0.08
    广东
    -0.08
    娱乐场
    -0.08
     Johannesburg
    -0.08
     Yem
    -0.08
    POSITIVE LOGITS
    chini
    0.15
     noodles
    0.10
    hetti
    0.09
    olini
    0.09
     blossoms
    0.09
    chine
    0.09
    cone
    0.08
    chinen
    0.08
     sauté
    0.08
    িনি
    0.08
    Activations Density 0.003%

    No Known Activations