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. 119314
    Prev
    Next
    INDEX
    Explanations

    chatbot responses

    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
    дз
    -0.08
    404
    -0.07
     presidente
    -0.07
    434
    -0.07
     policía
    -0.07
     tb
    -0.07
    tb
    -0.07
    (confirm
    -0.07
     strenuous
    -0.07
    CCE
    -0.07
    POSITIVE LOGITS
     
    0.14
    യില്
    0.09
    ​
    0.09
     riktigt
    0.08
    &nbsp
    0.08
    ೂರ
    0.08
     നിര്
    0.08
     évo
    0.08
    

    0.08
     ​
    0.08
    Activations Density 0.340%

    No Known Activations