© 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. 44626
    Prev
    Next
    INDEX
    Explanations

    同比

    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
    Than
    -0.08
    �
    -0.08
    、更
    -0.08
    ví
    -0.08
    than
    -0.07
    -than
    -0.07
    ží
    -0.07
     atualmente
    -0.07
     até
    -0.07
    رخ
    -0.07
    POSITIVE LOGITS
     changed
    0.08
     kuongeza
    0.08
     ndry
    0.07
     gad
    0.07
     pawn
    0.07
    енә
    0.07
     बदल
    0.07
    asury
    0.07
     �
    0.07
    ära
    0.07
    Activations Density 0.003%

    No Known Activations