© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44640
    Prev
    Next
    INDEX
    Explanations

    203

    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
     lone
    -0.09
     damal
    -0.08
     Anaheim
    -0.07
    	val
    -0.07
     بالص
    -0.07
    NOS
    -0.07
     Dro
    -0.07
     yep
    -0.07
     Lance
    -0.07
    YES
    -0.07
    POSITIVE LOGITS
     ambitie
    0.09
     prospects
    0.09
     idéal
    0.09
    予定
    0.09
     સુધી
    0.09
     prospect
    0.09
    预计
    0.09
     sustainably
    0.09
     nanti
    0.08
     القادمة
    0.08
    Activations Density 0.012%

    No Known Activations