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

    Neuronpedia

    Jacobian LensNEW
    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. 63813
    Prev
    Next
    INDEX
    Explanations

    if and colon

    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
     cancellations
    -0.08
     politician
    -0.08
    자로
    -0.08
    Ра
    -0.08
    술
    -0.08
     prostu
    -0.08
     transaction
    -0.08
    Таким
    -0.08
    자
    -0.07
    exclusive
    -0.07
    POSITIVE LOGITS
     warning
    0.10
    	found
    0.09
    _warning
    0.09
    Found
    0.09
     نصب
    0.09
     Found
    0.09
     found
    0.09
    Warning
    0.09
    _require
    0.08
     Warning
    0.08
    Activations Density 0.010%

    No Known Activations