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. 49061
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    Traffic
    -0.09
     traffic
    -0.09
     Traffic
    -0.09
     circ
    -0.08
     contraction
    -0.08
    traffic
    -0.08
     viewer
    -0.08
     learns
    -0.08
     capture
    -0.07
     Skull
    -0.07
    POSITIVE LOGITS
    	err
    0.10
    Err
    0.10
    (err
    0.10
     lỗi
    0.10
    .Err
    0.10
    .try
    0.10
     err
    0.09
     NSError
    0.09
    _ERR
    0.09
     incurred
    0.09
    Activations Density 0.004%

    No Known Activations