© 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. 7778
    Prev
    Next
    INDEX
    Explanations

    switch

    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
     avenue
    -0.09
    	fd
    -0.07
    ไว้
    -0.07
     Uncle
    -0.07
    viet
    -0.07
    Luck
    -0.07
    ursal
    -0.07
    ır
    -0.07
     שנות
    -0.07
    arium
    -0.07
    POSITIVE LOGITS
     wechseln
    0.13
     transition
    0.12
     transitions
    0.12
     Transition
    0.11
     переключ
    0.11
     abrupt
    0.11
     transición
    0.11
    -transition
    0.11
     switches
    0.11
    换
    0.11
    Activations Density 0.020%

    No Known Activations