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. 131051
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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
     долгов
    -0.09
    ås
    -0.08
    ographique
    -0.08
    ienna
    -0.08
    лица
    -0.08
     må
    -0.08
    aites
    -0.08
     usage
    -0.08
    /Subthreshold
    -0.07
    étation
    -0.07
    POSITIVE LOGITS
    ్చ
    0.08
    generic
    0.08
     Ag
    0.08
    ('_
    0.07
     whai
    0.07
    Ag
    0.07
    Authority
    0.07
    rating
    0.07
    _generic
    0.07
    CONF
    0.07
    Activations Density 0.000%

    No Known Activations