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. 90075
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ੰਦਰ
    -0.08
    úde
    -0.08
    ,道
    -0.08
    Guide
    -0.08
     dignity
    -0.07
     данном
    -0.07
     Rajasthan
    -0.07
     достоин
    -0.07
     менш
    -0.07
     décès
    -0.07
    POSITIVE LOGITS
     xuyên
    0.11
     habits
    0.10
    习
    0.09
     regelmäßig
    0.09
     worship
    0.09
     regularly
    0.09
     hábitos
    0.08
     frequent
    0.08
     enjoy
    0.08
     fazia
    0.08
    Activations Density 0.121%

    No Known Activations