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. 56000
    Prev
    Next
    INDEX
    Explanations

    social

    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
    ેસ
    -0.07
     philosophers
    -0.07
     mulle
    -0.07
    -like
    -0.07
     Prague
    -0.07
     Nuk
    -0.07
    lear
    -0.07
     atlas
    -0.07
     â
    -0.07
     inteligentes
    -0.06
    POSITIVE LOGITS
    izabeth
    0.09
     Leitung
    0.08
    ическими
    0.08
     अचानक
    0.08
     danach
    0.08
     resist
    0.07
    éric
    0.07
    到底
    0.07
     עצמי
    0.07
     oz
    0.07
    Activations Density 0.244%

    No Known Activations