© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29474
    Prev
    Next
    INDEX
    Explanations

    page size specifications

    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
     Zanzibar
    -0.09
     friendships
    -0.09
    _jump
    -0.08
    �
    -0.08
     Jump
    -0.08
     zeal
    -0.08
     glimpse
    -0.08
     zend
    -0.08
     Generalitat
    -0.08
     Bengaluru
    -0.07
    POSITIVE LOGITS
    尺寸
    0.13
    サイズ
    0.11
     size
    0.10
    -size
    0.09
     आकार
    0.09
    (size
    0.09
    _SIZE
    0.09
    -sized
    0.09
     dimensions
    0.09
     giấy
    0.09
    Activations Density 0.015%

    No Known Activations