© 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. 54515
    Prev
    Next
    INDEX
    Explanations

    per

    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
     регистра
    -0.08
     ممن
    -0.08
    arım
    -0.07
    త్వ
    -0.07
    ])
    -0.07
    =\
    -0.07
     задания
    -0.07
     বিজ
    -0.07
    ={
    -0.07
     الشرقية
    -0.07
    POSITIVE LOGITS
     individual's
    0.10
    消费
    0.10
     promedio
    0.10
     person's
    0.10
     člov
    0.10
     annually
    0.10
     सेवन
    0.10
     habitudes
    0.09
     gemiddeld
    0.09
     sedent
    0.09
    Activations Density 0.038%

    No Known Activations