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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12877
    Prev
    Next
    INDEX
    Explanations

    Frontiers journal

    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
    铺
    -0.08
    -0.08
     zieht
    -0.07
    迁
    -0.07
     hil
    -0.07
     cakes
    -0.07
    下来
    -0.07
     recognizes
    -0.07
     saisir
    -0.07
     Lisa
    -0.07
    POSITIVE LOGITS
    _pop
    0.08
    lycer
    0.08
     aquatic
    0.08
    _a
    0.08
     корпоратив
    0.07
     hippoc
    0.07
    _MEMORY
    0.07
    acea
    0.07
     neuroscience
    0.07
     Oper
    0.07
    Activations Density 0.003%

    No Known Activations