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. 60876
    Prev
    Next
    INDEX
    Explanations

    .start

    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
    pons
    -0.08
     lesser
    -0.07
    duc
    -0.07
     operator
    -0.07
    >;
    -0.07
     engineered
    -0.07
    lec
    -0.07
    setting
    -0.07
     solved
    -0.07
     Dar
    -0.07
    POSITIVE LOGITS
     Katonda
    0.10
     вэ
    0.09
     Modimo
    0.08
    otherapie
    0.08
    !"↵↵
    0.08
     tanggal
    0.08
    éo
    0.08
      
    0.08
     Pep
    0.08
     הראשון
    0.08
    Activations Density 0.001%

    No Known Activations