© 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. 65549
    Prev
    Next
    INDEX
    Explanations

    answer

    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
     freaking
    -0.08
     WTF
    -0.08
     tramo
    -0.07
     Kry
    -0.07
     brand
    -0.07
     tribe
    -0.07
     steken
    -0.07
     tratar
    -0.07
     manchen
    -0.07
     brands
    -0.07
    POSITIVE LOGITS
     babagan
    0.09
     للغاية
    0.08
    ，例如
    0.08
     respecto
    0.08
    akin
    0.08
    ，并
    0.07
    ，比如
    0.07
     જેથી
    0.07
    	Value
    0.07
    ennent
    0.07
    Activations Density 0.022%

    No Known Activations