© 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. 15-RESID-POST-AA
    11. 16693
    Prev
    Next
    INDEX
    Explanations

    expected

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     კანდ
    -0.18
     彩神争霸网站
    -0.18
     银航
    -0.18
     天天中彩票提款
    -0.18
     重庆时时彩杀
    -0.18
     天天中奖彩票
    -0.18
     天天中彩票被
    -0.18
    -0.18
    -0.18
    -0.18
    POSITIVE LOGITS
    ↵↵
    0.13
     e
    0.11
    <|reserved_200016|>
    0.11
     a
    0.11
    ..↵↵
    0.11
     this
    0.11
     ,
    0.11
    ...↵↵
    0.11
    ��
    0.10
    ↵↵↵
    0.10
    Activations Density 1.066%
    No Known Activations