© 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. 64882
    Prev
    Next
    INDEX
    Explanations

    conditional checks

    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
    વાદ
    -0.08
     delivery
    -0.08
    TXT
    -0.07
     TXT
    -0.07
    .const
    -0.07
    默
    -0.07
     тран
    -0.07
     SL
    -0.07
     التض
    -0.07
    .cached
    -0.07
    POSITIVE LOGITS
     判断
    0.09
     условия
    0.09
    termination
    0.09
    检查
    0.09
     Check
    0.09
    maine
    0.09
    Check
    0.08
    _continue
    0.08
    Termination
    0.08
     beurte
    0.08
    Activations Density 0.010%

    No Known Activations