Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60731
    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
     Twain
    -0.10
     SWOT
    -0.10
     county
    -0.10
    deck
    -0.09
     pamph
    -0.09
     deck
    -0.09
     welcoming
    -0.09
    County
    -0.09
     xmlhttp
    -0.09
     investigative
    -0.09
    POSITIVE LOGITS
     tensors
    0.19
     tensor
    0.19
    (torch
    0.19
     logits
    0.19
    Tensor
    0.18
    _tensor
    0.18
    tensor
    0.18
    .Tensor
    0.17
    .tensor
    0.17
     Tensor
    0.17
    Activations Density 0.031%

    No Known Activations