© 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. 5513
    Prev
    Next
    INDEX
    Explanations

    急

    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
    -0.10
    ovascular
    -0.08
     ange
    -0.08
    고
    -0.08
    ulle
    -0.08
    anns
    -0.07
    owe
    -0.07
     côt
    -0.07
    '*
    -0.07
    ioxide
    -0.07
    POSITIVE LOGITS
    促
    0.12
    救
    0.11
    剧
    0.11
    itación
    0.11
    itating
    0.10
    躁
    0.10
    诊
    0.09
    先锋
    0.09
    kẹ
    0.09
    促进
    0.09
    Activations Density 0.001%
    No Known Activations