© 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. 11-RESID-POST-AA
    11. 110544
    Prev
    Next
    INDEX
    Explanations

    word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confortable
    -0.09
     comfortabele
    -0.09
    舒
    -0.08
     comfortabel
    -0.08
     aches
    -0.08
     confort
    -0.08
    库存
    -0.08
     komfort
    -0.08
     comfort
    -0.08
     heats
    -0.07
    POSITIVE LOGITS
    Starts
    0.12
     시작
    0.12
    Prefixes
    0.12
    Prefix
    0.12
    -prefix
    0.11
    .starts
    0.11
    .Starts
    0.11
     തുടങ്ങ
    0.11
    (prefix
    0.11
     beginnt
    0.11
    Activations Density 0.032%

    No Known Activations