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. 75952
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
    UTE
    -0.09
    出了
    -0.08
     houding
    -0.08
    UTOR
    -0.08
     Keskimäär
    -0.08
     Haltung
    -0.08
    čila
    -0.08
     voul
    -0.08
     معیار
    -0.08
     стадии
    -0.08
    POSITIVE LOGITS
     someday
    0.08
    url
    0.08
    oa
    0.07
     rigor
    0.07
     воз
    0.07
    oas
    0.07
     stewardship
    0.07
    共同
    0.07
    /j
    0.07
    tat
    0.07
    Activations Density 0.007%

    No Known Activations