© 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. 31180
    Prev
    Next
    INDEX
    Explanations

    exclusivity

    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
     fonts
    -0.08
    粮
    -0.08
    াণ্ড
    -0.08
    үп
    -0.08
    金币
    -0.07
     mung
    -0.07
     hil
    -0.07
    韩
    -0.07
    -cü
    -0.07
     astronomy
    -0.07
    POSITIVE LOGITS
    期間
    0.08
     रहने
    0.08
     périodes
    0.08
    Period
    0.08
     ನ
    0.08
     मेहन
    0.08
    -direction
    0.08
     vissa
    0.08
     기간
    0.08
     अवधि
    0.08
    Activations Density 0.002%

    No Known Activations