© 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. 108567
    Prev
    Next
    INDEX
    Explanations

    concerned

    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
    ůj
    -0.08
    ින
    -0.07
     לח
    -0.07
     தொடர்ப
    -0.07
    (class
    -0.07
     ós
    -0.07
     ప్రమ
    -0.07
     עסק
    -0.07
    Copyright
    -0.07
    -0.07
    POSITIVE LOGITS
    抱
    0.11
    路线
    0.09
    看到
    0.09
    之前
    0.08
    策略
    0.08
    找到
    0.08
     Farben
    0.08
     spir
    0.07
    负责
    0.07
    继续
    0.07
    Activations Density 0.073%
    No Known Activations