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. 76550
    Prev
    Next
    INDEX
    Explanations

    GPU memory

    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
    民
    -0.09
     údaj
    -0.09
     муницип
    -0.09
    公益
    -0.09
     luật
    -0.09
     образования
    -0.09
    百科
    -0.08
    刻
    -0.08
    厘
    -0.08
     prestigious
    -0.08
    POSITIVE LOGITS
     GPUs
    0.15
     GPU
    0.12
     gpu
    0.11
     Batch
    0.11
    _gpu
    0.10
    GPU
    0.09
     RAM
    0.09
     CUDA
    0.09
    gpu
    0.09
     batch
    0.09
    Activations Density 0.004%

    No Known Activations