© 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. 54469
    Prev
    Next
    INDEX
    Explanations

    from

    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
    bok
    -0.09
    wl
    -0.08
    esty
    -0.07
     everyone's
    -0.07
    惠
    -0.07
    (/[
    -0.07
    778
    -0.07
    랑
    -0.07
    -base
    -0.07
    kir
    -0.07
    POSITIVE LOGITS
    准备
    0.11
     તૈય
    0.10
     તૈયાર
    0.10
     തയ്യാറ
    0.10
     preparação
    0.10
     готов
    0.10
     Preparing
    0.09
     Setup
    0.09
    	raw
    0.09
    .Setup
    0.09
    Activations Density 0.011%

    No Known Activations