© 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. 49136
    Prev
    Next
    INDEX
    Explanations

    video tutorials

    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
    ＝
    -0.09
     كش
    -0.08
     lors
    -0.07
     mott
    -0.07
     ส่ง
    -0.07
    Mensagem
    -0.07
     رسالة
    -0.07
    -information
    -0.07
     incapable
    -0.07
     అంటే
    -0.07
    POSITIVE LOGITS
     tutorials
    0.19
    免费视频
    0.18
    教程
    0.17
    免费观看
    0.17
    视频免费
    0.16
    免费资料
    0.16
     gratuits
    0.15
     Tutorials
    0.15
    免费在线观看
    0.15
    免费高清
    0.15
    Activations Density 0.062%

    No Known Activations