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. 48961
    Prev
    Next
    INDEX
    Explanations

    Arabic

    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
     Kansas
    -0.08
     quen
    -0.08
    quil
    -0.08
     erhö
    -0.07
     Schra
    -0.07
    izziness
    -0.07
     pressured
    -0.07
    ilsen
    -0.07
     upheld
    -0.07
     syringe
    -0.07
    POSITIVE LOGITS
     Arabic
    0.10
     العربية
    0.09
     Assamese
    0.09
    Arabic
    0.08
     memes
    0.08
    ‎
    0.08
     verses
    0.08
     Chinese
    0.08
    ا
    0.08
    ️
    0.07
    Activations Density 0.006%

    No Known Activations