© 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. 7632
    Prev
    Next
    INDEX
    Explanations

    Explanations and guides

    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
    Danger
    -0.08
     Danger
    -0.08
     disabling
    -0.07
    <|reserved_200016|>
    -0.07
     danger
    -0.07
    disable
    -0.07
     doubt
    -0.07
     disable
    -0.07
    danger
    -0.07
     ree
    -0.07
    POSITIVE LOGITS
    。另外
    0.08
     ಬಾಲ
    0.08
     posteriormente
    0.08
    afy
    0.08
     ಕೂಡ
    0.08
    ಾ�
    0.08
     tampoco
    0.08
     तथा
    0.08
     panties
    0.08
    ọ́
    0.07
    Activations Density 0.346%

    No Known Activations