© 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. 99764
    Prev
    Next
    INDEX
    Explanations

    written

    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
    वा
    -0.08
    बाक
    -0.08
    लोक
    -0.07
    منٹ
    -0.07
     béné
    -0.07
    חל
    -0.07
    ."""
    -0.07
    בתי
    -0.07
    Wilson
    -0.07
     cherch
    -0.07
    POSITIVE LOGITS
     Госп
    0.10
    	top
    0.09
     obtainable
    0.08
     تعالى
    0.08
     ره
    0.08
     attainable
    0.07
    ounced
    0.07
     experimentation
    0.07
     топ
    0.07
     آخر
    0.07
    Activations Density 0.008%

    No Known Activations