Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98513
    Prev
    Next
    INDEX
    Explanations

    T

    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
     рус
    -0.08
     nationality
    -0.08
     podremos
    -0.08
     рублей
    -0.07
    Nationality
    -0.07
     franca
    -0.07
     бос
    -0.07
     руб
    -0.07
     Exhibition
    -0.07
     maß
    -0.07
    POSITIVE LOGITS
    ark
    0.09
    ila
    0.09
    untur
    0.09
    arkt
    0.09
    ido
    0.08
    iety
    0.08
    ARK
    0.08
    KL
    0.08
    ode
    0.08
    unte
    0.08
    Activations Density 0.000%

    No Known Activations