© 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. 44285
    Prev
    Next
    INDEX
    Explanations

    Programming code

    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
     freeway
    -0.08
     Chil
    -0.08
    :https
    -0.07
    仕事
    -0.07
    är
    -0.07
     Sol
    -0.07
     inflam
    -0.07
     male
    -0.07
     dictates
    -0.07
    created
    -0.07
    POSITIVE LOGITS
     JFile
    0.09
     ಮಾಡಲು
    0.09
     查看
    0.09
     наж
    0.09
     asistencia
    0.08
     comando
    0.08
     thao
    0.08
     جاري
    0.08
     deseas
    0.08
     COMMAND
    0.08
    Activations Density 0.015%

    No Known Activations