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. 106083
    Prev
    Next
    INDEX
    Explanations

    Mathematics

    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
     avión
    -0.08
    开启
    -0.08
    _excel
    -0.08
     avo
    -0.08
     ഏ
    -0.07
     avião
    -0.07
    GEN
    -0.07
    AVE
    -0.07
    nti
    -0.07
    运动
    -0.07
    POSITIVE LOGITS
     éventuellement
    0.09
    árez
    0.09
    oriasis
    0.08
    스로
    0.08
     finalmente
    0.08
     schließlich
    0.08
     otro
    0.08
     télé
    0.08
     finalement
    0.08
     animals
    0.08
    Activations Density 0.219%

    No Known Activations