© 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. 11-RESID-POST-AA
    11. 77825
    Prev
    Next
    INDEX
    Explanations

    label

    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
    သူ
    -0.07
     Technologien
    -0.07
    ppa
    -0.07
     Sun
    -0.07
     ethos
    -0.07
    Sun
    -0.07
     Serum
    -0.07
     Japon
    -0.07
    veni
    -0.07
    Lifestyle
    -0.07
    POSITIVE LOGITS
    轴
    0.09
    (TAG
    0.09
    /tag
    0.09
    abcdefghijklmnopqrstuvwxyz
    0.08
    _Tag
    0.08
    皇冠
    0.08
     gọi
    0.08
    ைப்பட
    0.08
     धन
    0.08
     гир
    0.08
    Activations Density 0.005%

    No Known Activations