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. 12760
    Prev
    Next
    INDEX
    Explanations

    programming languages

    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
     Superstar
    -0.09
     hems
    -0.09
     rues
    -0.08
     percussion
    -0.08
     flim
    -0.08
     tits
    -0.08
     razem
    -0.08
     Combination
    -0.08
     ruas
    -0.08
    ADVERTISEMENT
    -0.08
    POSITIVE LOGITS
     SDK
    0.11
    客户端
    0.11
    Python
    0.10
     clients
    0.10
     Java
    0.10
     Python
    0.09
    (language
    0.09
    SDK
    0.09
     지원
    0.09
    _python
    0.09
    Activations Density 0.016%

    No Known Activations