© 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. 7723
    Prev
    Next
    INDEX
    Explanations

    1

    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
    -pass
    -0.08
     laga
    -0.08
     pass
    -0.08
     cared
    -0.08
    _quotes
    -0.08
     Ina
    -0.08
    体育彩票
    -0.07
    盖
    -0.07
     stanza
    -0.07
     سيارات
    -0.07
    POSITIVE LOGITS
     wired
    0.08
    	common
    0.07
     Break
    0.07
    ické
    0.07
     wal
    0.07
    0.07
    bedo
    0.07
    noj
    0.07
     piled
    0.07
     sólida
    0.07
    Activations Density 0.021%
    No Known Activations