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. 109687
    Prev
    Next
    INDEX
    Explanations

    tensors and indices

    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
     sublim
    -0.09
     svm
    -0.08
     cravings
    -0.08
     moderation
    -0.08
    itaire
    -0.08
     Wyatt
    -0.08
     slug
    -0.08
    ipal
    -0.08
    分享
    -0.08
     '~/
    -0.07
    POSITIVE LOGITS
     tensor
    0.12
    tensor
    0.11
     indices
    0.11
     tensors
    0.10
    indices
    0.10
    Indices
    0.10
    Tensor
    0.09
    _tensor
    0.09
     contracted
    0.09
     ministers
    0.09
    Activations Density 0.006%

    No Known Activations