© 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. 69587
    Prev
    Next
    INDEX
    Explanations

    chatbot turn taking

    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
    代引
    -0.08
    Eventually
    -0.08
     Hunts
    -0.08
    discount
    -0.07
     metabolism
    -0.07
     formulas
    -0.07
     Wär
    -0.07
     zarar
    -0.07
    damage
    -0.07
     ков
    -0.07
    POSITIVE LOGITS
     minimalist
    0.13
    简单
    0.12
    简
    0.12
     terse
    0.12
     concise
    0.12
     succinct
    0.12
     brief
    0.11
     simple
    0.10
     بسيطة
    0.10
    单
    0.10
    Activations Density 0.132%

    No Known Activations