Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43815
    Prev
    Next
    INDEX
    Explanations

    Non-English

    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
     وقد
    -0.09
     KO
    -0.09
     feeder
    -0.08
    blocking
    -0.08
     Kimber
    -0.08
     ROUT
    -0.08
     للك
    -0.08
     قدرة
    -0.08
     режима
    -0.08
    étr
    -0.08
    POSITIVE LOGITS
    Conclusion
    0.17
     conclusion
    0.16
     Conclusion
    0.16
     conclusión
    0.15
     concluded
    0.14
    Conclus
    0.14
     concluding
    0.14
    总结
    0.14
     conclusions
    0.14
     conclude
    0.14
    Activations Density 0.011%

    No Known Activations