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. 55641
    Prev
    Next
    INDEX
    Explanations

    Chinese code snippets

    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
    ويل
    -0.08
    hint
    -0.08
     desirable
    -0.07
     hints
    -0.07
    odzi
    -0.07
    buffer
    -0.07
    ves
    -0.07
     naive
    -0.07
    wich
    -0.06
     hint
    -0.06
    POSITIVE LOGITS
     rõ
    0.09
    姓
    0.09
     ఖ
    0.08
     আমি
    0.08
    今回は
    0.08
    agonia
    0.08
    列
    0.08
     ذکر
    0.08
    عضاء
    0.08
     खाते
    0.08
    Activations Density 0.004%

    No Known Activations