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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 179
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     sorry
    -0.08
     ಗುರು
    -0.08
     Friend
    -0.08
     mistaken
    -0.07
    ированных
    -0.07
     encontrada
    -0.07
     знаком
    -0.07
     );
    -0.07
     ),
    -0.07
     ઓળખ
    -0.07
    POSITIVE LOGITS
    =tk
    0.09
     expands
    0.09
     adaptability
    0.08
     وث
    0.08
    Applic
    0.08
     زیرا
    0.08
     vontade
    0.08
     zowel
    0.08
    Bindable
    0.08
    ทั้ง
    0.08
    Activations Density 0.000%

    No Known Activations