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. 65267
    Prev
    Next
    INDEX
    Explanations

    programming 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
    Residents
    -0.10
     parish
    -0.09
     municipal
    -0.09
     주민
    -0.09
     patron
    -0.09
     ನಿವಾಸ
    -0.09
    Municip
    -0.09
     Legislative
    -0.09
    居民
    -0.09
     paradox
    -0.09
    POSITIVE LOGITS
     pretrained
    0.15
     CUDA
    0.15
    CUDA
    0.15
    训练
    0.14
     torchvision
    0.14
     sklearn
    0.14
     training
    0.14
     checkpoint
    0.13
    (torch
    0.13
     Tensor
    0.13
    Activations Density 0.038%

    No Known Activations