© 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. 3-RESID-POST-AA
    11. 3141
    Prev
    Next
    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ми
    -0.08
     monitoring
    -0.07
    achu
    -0.07
    isu
    -0.07
     cyber
    -0.07
     Malibu
    -0.07
     cerca
    -0.07
     prison
    -0.07
     сопров
    -0.07
    Sw
    -0.07
    POSITIVE LOGITS
    ொட
    0.08
    灭
    0.08
     Micros
    0.08
     sayı
    0.08
     ગીત
    0.07
    िरे
    0.07
    HAS
    0.07
     Slowly
    0.07
     offending
    0.07
    ધી
    0.07
    Activations Density 0.003%

    No Known Activations