© 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. 23-RESID-POST-AA
    11. 48948
    Prev
    Next
    INDEX
    Explanations

    son

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ელად
    -0.09
    имо
    -0.08
    ុល
    -0.08
     modular
    -0.08
    Attach
    -0.08
    zeniem
    -0.08
    ელია
    -0.07
    хон
    -0.07
    കേരള
    -0.07
     discounted
    -0.07
    POSITIVE LOGITS
    dee
    0.08
    dieren
    0.08
    ajas
    0.08
    icación
    0.08
     inteligentes
    0.08
    erezh
    0.07
     statues
    0.07
    oro
    0.07
    dea
    0.07
     estarán
    0.07
    Activations Density 0.002%

    No Known Activations