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. 11-RESID-POST-AA
    6. 88299
    Prev
    Next
    INDEX
    Explanations

    French language

    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
     имеется
    -0.08
    .config
    -0.08
     hehe
    -0.07
     ilustr
    -0.07
    ############################################################################
    -0.07
     unresolved
    -0.07
     curled
    -0.07
     unor
    -0.07
     though
    -0.07
     sistemas
    -0.07
    POSITIVE LOGITS
    France
    0.12
     Duch
    0.11
     Loire
    0.10
     France
    0.10
    Fran
    0.10
     Frankreich
    0.10
     Ligne
    0.10
    Lire
    0.09
     Dijon
    0.09
    Donc
    0.09
    Activations Density 0.067%

    No Known Activations