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. 59060
    Prev
    Next
    INDEX
    Explanations

    v

    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
     હતી
    -0.09
     ભાષ
    -0.08
     workshops
    -0.08
     વધી
    -0.08
     workshop
    -0.08
     હતો
    -0.08
     Workshops
    -0.08
     હતું
    -0.08
     થી
    -0.08
     થયો
    -0.08
    POSITIVE LOGITS
    �
    0.08
     aŭ
    0.08
     вним
    0.08
     прежде
    0.08
     pertinent
    0.08
    探
    0.07
     ауд
    0.07
    zell
    0.07
    ︎
    0.07
     alvast
    0.07
    Activations Density 0.030%

    No Known Activations