© 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. 99577
    Prev
    Next
    INDEX
    Explanations

    **

    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
     Auß
    -0.08
    lasse
    -0.08
     leh
    -0.08
     Daarna
    -0.08
    lilik
    -0.08
    elm
    -0.08
    chu
    -0.08
     Suomen
    -0.08
     sameng
    -0.08
     Hana
    -0.08
    POSITIVE LOGITS
    ぜひ
    0.07
    0.07
     importantes
    0.07
     neutral
    0.07
    sten
    0.07
    ेश
    0.07
     ಗೆ
    0.07
     innovate
    0.07
     innovative
    0.07
     importantly
    0.07
    Activations Density 0.041%

    No Known Activations