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. 60177
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ို့
    -0.08
     trend
    -0.08
     concurrency
    -0.08
    әт
    -0.08
    趋势
    -0.08
    ရှိ
    -0.08
    ಿದ್ದರು
    -0.07
     trends
    -0.07
    .TR
    -0.07
     richt
    -0.07
    POSITIVE LOGITS
     nhau
    0.09
     respecto
    0.09
     tino
    0.09
     betrekking
    0.09
     vold
    0.08
    yll
    0.08
    不上
    0.08
    adox
    0.08
     jeans
    0.08
     ří
    0.08
    Activations Density 0.173%

    No Known Activations