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. 45498
    Prev
    Next
    INDEX
    Explanations

    Story beginnings with dates

    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
     frequently
    -0.08
     shading
    -0.08
     benchmarking
    -0.07
     agress
    -0.07
     efficiently
    -0.07
    nofollow
    -0.07
     synonyms
    -0.07
    senal
    -0.07
     controversies
    -0.07
    veel
    -0.07
    POSITIVE LOGITS
     yılında
    0.10
    ณะที่
    0.09
     Estes
    0.08
     gdy
    0.08
     هنگ
    0.08
    ,当
    0.08
     Isis
    0.08
     solitude
    0.08
     مساء
    0.08
    暮
    0.08
    Activations Density 0.048%

    No Known Activations