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

    Neuronpedia

    Jacobian LensNEW
    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. 112569
    Prev
    Next
    INDEX
    Explanations

    global politics, "new world order"

    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
    -themed
    -0.08
     hadn't
    -0.08
     tivesse
    -0.08
     کل
    -0.08
    kyt
    -0.07
    lu
    -0.07
     phrase
    -0.07
     práct
    -0.07
     moderate
    -0.07
    Moder
    -0.07
    POSITIVE LOGITS
    骗局
    0.10
    骗
    0.09
    导致
    0.09
     hyst
    0.09
     أمريكا
    0.08
    邪
    0.08
    骗子
    0.08
    (save
    0.08
     wrongly
    0.08
    	save
    0.08
    Activations Density 0.161%

    No Known Activations