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. 43775
    Prev
    Next
    INDEX
    Explanations

    ом

    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
    페이지
    -0.08
     splitted
    -0.08
    'aide
    -0.08
    .cd
    -0.08
     duro
    -0.08
     necesita
    -0.07
     Dans
    -0.07
    WO
    -0.07
    avu
    -0.07
    Dans
    -0.07
    POSITIVE LOGITS
     сниз
    0.08
    дей
    0.08
     如意
    0.08
     Surprisingly
    0.08
     olev
    0.08
     �
    0.07
     rebel
    0.07
     Revol
    0.07
    дай
    0.07
     举报
    0.07
    Activations Density 0.001%

    No Known Activations