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. 53959
    Prev
    Next
    INDEX
    Explanations

    Hamlet

    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
    иро
    -0.08
    _core
    -0.08
    _Mod
    -0.08
     aplikasyon
    -0.08
     socket
    -0.07
    iriman
    -0.07
     aprendizado
    -0.07
    -mod
    -0.07
    rodní
    -0.07
    _SCOPE
    -0.07
    POSITIVE LOGITS
    前三
    0.07
     فساد
    0.07
     જોઇ
    0.07
     ezi
    0.07
     первой
    0.07
    聘
    0.07
     inga
    0.07
     zašt
    0.07
     eerst
    0.07
     Eating
    0.07
    Activations Density 0.002%

    No Known Activations