Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11744
    Prev
    Next
    INDEX
    Explanations

    micro

    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
     powers
    -0.08
     מוג
    -0.08
     MATLAB
    -0.08
    Plug
    -0.08
    UMP
    -0.08
     Plug
    -0.08
    _callable
    -0.08
    	manager
    -0.07
    powers
    -0.07
     scheduling
    -0.07
    POSITIVE LOGITS
    .feedback
    0.08
    .match
    0.08
     öğ
    0.08
    _ELEMENTS
    0.08
     confirmations
    0.08
     {:?
    0.08
    反馈
    0.08
    .Button
    0.08
     شکست
    0.08
    -match
    0.08
    Activations Density 0.002%

    No Known Activations