© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 50304
    Prev
    Next
    INDEX
    Explanations

    Webpage snippets

    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
    ijek
    -0.09
     कै
    -0.07
    инек
    -0.07
     reactive
    -0.07
     air
    -0.07
    ске
    -0.07
     Evalu
    -0.07
     Ano
    -0.07
     catalyst
    -0.07
     trigger
    -0.07
    POSITIVE LOGITS
     acces
    0.09
     доступ
    0.09
     posl
    0.08
     accessibles
    0.08
    Scrolling
    0.08
    还是
    0.08
     disponibilidad
    0.08
     görd
    0.08
    Accessibility
    0.08
     ઉપલબ્ધ
    0.08
    Activations Density 0.001%

    No Known Activations