© 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. 45775
    Prev
    Next
    INDEX
    Explanations

    to

    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
    breaker
    -0.08
    古
    -0.08
    _entropy
    -0.08
    加工
    -0.08
     Reynolds
    -0.07
     Antiqu
    -0.07
     गुण
    -0.07
     erupted
    -0.07
     quaisquer
    -0.07
    ಿಮ
    -0.07
    POSITIVE LOGITS
     �
    0.08
     fore
    0.08
     aconse
    0.08
    얼
    0.08
     rob
    0.08
    .git
    0.08
    �
    0.08
     wiz
    0.08
    (fid
    0.07
    фта
    0.07
    Activations Density 0.013%

    No Known Activations