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. 111715
    Prev
    Next
    INDEX
    Explanations

    ият

    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
    /Test
    -0.09
    Regexp
    -0.08
    _On
    -0.08
     Rally
    -0.07
     Trigger
    -0.07
     mediante
    -0.07
    resent
    -0.07
    FIN
    -0.07
     Watkins
    -0.07
     Tipo
    -0.07
    POSITIVE LOGITS
     शुभ
    0.11
    好运
    0.11
     શુભ
    0.10
     enjoy
    0.10
     শুভ
    0.10
     감사합니다
    0.10
    Enjoy
    0.09
     tengas
    0.09
    !"↵
    0.09
    !'↵
    0.09
    Activations Density 0.013%

    No Known Activations