© 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. 64824
    Prev
    Next
    INDEX
    Explanations

    options in code

    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
     Veterinary
    -0.08
     Amph
    -0.08
    ్వర
    -0.08
     //{↵
    -0.08
     rozpoc
    -0.08
     악
    -0.07
     Ally
    -0.07
     //$
    -0.07
     quaisquer
    -0.07
    ಕ್ಷಿಣ
    -0.07
    POSITIVE LOGITS
     opción
    0.12
    option
    0.11
    alternative
    0.11
     opção
    0.11
     optar
    0.11
    Option
    0.10
     alternativa
    0.10
     alternatives
    0.10
     vaihtoe
    0.10
    recommended
    0.10
    Activations Density 0.043%

    No Known Activations