© 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. 31246
    Prev
    Next
    INDEX
    Explanations

    differential

    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
     Lotus
    -0.09
    力度
    -0.09
    ね
    -0.08
     soybean
    -0.08
    认可
    -0.08
     borough
    -0.08
    羽
    -0.08
    ől
    -0.08
     attribution
    -0.08
     tæ
    -0.07
    POSITIVE LOGITS
     equations
    0.10
     equation
    0.09
     PDE
    0.09
     solved
    0.08
    646
    0.08
    학교
    0.07
    bahn
    0.07
     समी
    0.07
    /d
    0.07
     describes
    0.07
    Activations Density 0.004%

    No Known Activations