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. 43855
    Prev
    Next
    INDEX
    Explanations

    loss, leaks, inefficiencies

    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
    _SW
    -0.08
    "K
    -0.08
     paix
    -0.08
    if
    -0.08
     wygl
    -0.07
     patches
    -0.07
    PATCH
    -0.07
     règle
    -0.07
    Then
    -0.07
    _patch
    -0.07
    POSITIVE LOGITS
     desperd
    0.14
     wasted
    0.13
     squander
    0.12
    泄
    0.12
     wast
    0.12
     waste
    0.12
     Leakage
    0.11
     Leak
    0.11
     leakage
    0.11
    漏
    0.11
    Activations Density 0.024%

    No Known Activations