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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45189
    Prev
    Next
    INDEX
    Explanations

    of

    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
     مسائل
    -0.08
     اخت
    -0.08
    قطاع
    -0.07
     arguably
    -0.07
     nuo
    -0.07
     לפחות
    -0.07
    \
    -0.07
     inutile
    -0.07
    ներից
    -0.07
    انی
    -0.07
    POSITIVE LOGITS
     будто
    0.11
     spacious
    0.09
     freshly
    0.09
     যেন
    0.09
     expertly
    0.08
     объем
    0.08
     vividly
    0.08
     grandeur
    0.08
     πως
    0.07
     whispered
    0.07
    Activations Density 0.009%

    No Known Activations