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. 13000
    Prev
    Next
    INDEX
    Explanations

    pencil

    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
     tub
    -0.08
    ",{
    -0.08
     시즌
    -0.08
     특히
    -0.08
    	template
    -0.08
    튜
    -0.08
     vieles
    -0.08
    یش
    -0.08
    XXXXXXXXXXXXXXXX
    -0.08
    vermogen
    -0.08
    POSITIVE LOGITS
     furn
    0.07
     ornaments
    0.07
     Sterling
    0.07
     fashion
    0.07
     verkrij
    0.07
    ਾਂ
    0.07
    _m
    0.07
     acclaim
    0.06
    /display
    0.06
    ع
    0.06
    Activations Density 0.092%

    No Known Activations