Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 49002
    Prev
    Next
    INDEX
    Explanations

    origami

    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
    iplier
    -0.08
    	override
    -0.08
     පහ
    -0.08
     인정
    -0.08
     inherited
    -0.08
     Patrice
    -0.08
     있어서
    -0.08
    Quotation
    -0.08
    遗漏
    -0.08
     employers
    -0.08
    POSITIVE LOGITS
     folding
    0.11
     fold
    0.09
     daun
    0.08
     orig
    0.08
     жу
    0.08
     Folding
    0.08
     folded
    0.08
     silk
    0.08
     Ku
    0.08
     folds
    0.08
    Activations Density 0.002%

    No Known Activations