© 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. 45600
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     konst
    -0.09
     αξ
    -0.08
     rost
    -0.08
     sulfur
    -0.08
     sulph
    -0.07
     exchange
    -0.07
     sicherlich
    -0.07
     가치
    -0.07
    weta
    -0.07
     المج
    -0.07
    POSITIVE LOGITS
    の場合
    0.11
    場合
    0.08
    corpor
    0.08
     большинства
    0.08
    /Linux
    0.07
     बाब
    0.07
    ажно
    0.07
    	if
    0.07
     Fuj
    0.07
     болсо
    0.07
    Activations Density 0.036%

    No Known Activations