© 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. 31640
    Prev
    Next
    INDEX
    Explanations

    my

    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
    ிருந்து
    -0.08
    systems
    -0.08
     저장
    -0.07
    رح
    -0.07
     Chor
    -0.07
    _revision
    -0.07
     bunk
    -0.07
    רד
    -0.07
     boosting
    -0.07
    oomla
    -0.07
    POSITIVE LOGITS
     руки
    0.14
     gloves
    0.14
     рук
    0.14
     Hände
    0.14
     glove
    0.14
    腕
    0.13
     হাত
    0.13
     claws
    0.13
     fingers
    0.13
     Gloves
    0.12
    Activations Density 0.108%

    No Known Activations