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. 11-RESID-POST-AA
    6. 106270
    Prev
    Next
    INDEX
    Explanations

    project

    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
    চিত
    -0.09
     bew
    -0.08
    人在
    -0.08
     conjunction
    -0.08
    事实上
    -0.08
     XR
    -0.07
     fapt
    -0.07
     obra
    -0.07
     menyebabkan
    -0.07
     nhi
    -0.07
    POSITIVE LOGITS
    (des
    0.08
    (topic
    0.08
    (address
    0.08
    (permission
    0.08
    helves
    0.07
     seç
    0.07
    (keyword
    0.07
    (title
    0.07
     Mohamed
    0.07
     istedi
    0.07
    Activations Density 0.007%

    No Known Activations