© 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. 6490
    Prev
    Next
    INDEX
    Explanations

    say "化"

    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
     ninete
    -0.11
     þr
    -0.11
    ulluni
    -0.11
     ทีเด็ด
    -0.11
     qinn
    -0.11
     ntej
    -0.10
    ผลบอล
    -0.10
     onns
    -0.10
     namm
    -0.10
    สิบเอ็ด
    -0.10
    POSITIVE LOGITS
     modernization
    0.11
     diversification
    0.10
    优化
    0.10
    (Route
    0.10
     optimization
    0.09
     automation
    0.09
    იზ
    0.09
    ализ
    0.09
    化
    0.09
     Optimization
    0.09
    Activations Density 0.006%

    No Known Activations