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. 65284
    Prev
    Next
    INDEX
    Explanations

    Record

    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
     diverted
    -0.08
     شکل
    -0.08
    �어
    -0.08
    تهاء
    -0.08
    hede
    -0.08
    \Requests
    -0.08
    annes
    -0.07
    იშვილი
    -0.07
    Stencil
    -0.07
     ڏئي
    -0.07
    POSITIVE LOGITS
    ஆ
    0.09
     except
    0.08
     WCHAR
    0.07
     Except
    0.07
    ఆ
    0.07
    overn
    0.07
     espe
    0.07
     Joe
    0.07
     ess
    0.07
    ச்ச
    0.07
    Activations Density 0.000%

    No Known Activations