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. 11671
    Prev
    Next
    INDEX
    Explanations

    .Module

    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
    049
    -0.09
     civilizations
    -0.09
    metadata
    -0.08
    ocado
    -0.08
    statuses
    -0.08
    019
    -0.08
    718
    -0.08
     गुणवत्ता
    -0.08
    793
    -0.08
     analytics
    -0.08
    POSITIVE LOGITS
     pretrained
    0.11
    .Module
    0.09
    .Sequential
    0.09
    (torch
    0.09
     tensors
    0.09
     torchvision
    0.09
     정의
    0.09
    .Tensor
    0.09
     구성
    0.08
     keras
    0.08
    Activations Density 0.006%

    No Known Activations