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. 30727
    Prev
    Next
    INDEX
    Explanations

    describes

    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
     }}
    ↵
    -0.08
     отоп
    -0.07
    디오
    -0.07
    ол
    -0.07
     annan
    -0.07
     anlat
    -0.07
    '])
    ↵
    -0.07
    ↵        
    ↵
    -0.07
     ?>
    ↵
    -0.07
     Sloven
    -0.07
    POSITIVE LOGITS
     applicable
    0.07
    297
    0.07
     প্রয়
    0.07
    Agency
    0.07
     glowing
    0.07
     attaching
    0.07
    ,可
    0.07
    ferences
    0.07
    Spam
    0.07
    zorg
    0.07
    Activations Density 0.012%

    No Known Activations