© 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. 45567
    Prev
    Next
    INDEX
    Explanations

    AI chatbot interaction

    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
    <|endoftext|>
    -0.13
    <|reserved_200016|>
    -0.11
     mé
    -0.08
    <Product
    -0.08
     tiêu
    -0.07
    ---------------↵
    -0.07
     driven
    -0.07
    576
    -0.07
     drivetrain
    -0.07
    -&
    -0.07
    POSITIVE LOGITS
     haha
    0.09
     Hitler
    0.08
    �이
    0.08
     XOR
    0.08
    Ya
    0.08
     intim
    0.07
    Actually
    0.07
     Etern
    0.07
    ราช
    0.07
     gap
    0.07
    Activations Density 0.015%

    No Known Activations