© 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. 54418
    Prev
    Next
    INDEX
    Explanations

    triangles

    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
     অতিথ
    -0.09
    ποίηση
    -0.09
    anethi
    -0.08
    ريحة
    -0.08
    ևոր
    -0.08
    UBLISH
    -0.08
     grootste
    -0.08
     sở
    -0.08
     Հայաստանը
    -0.08
     সন্তান
    -0.08
    POSITIVE LOGITS
    伸
    0.08
     Idi
    0.08
    uelas
    0.07
    ≫
    0.07
    Related
    0.07
    �
    0.07
    olver
    0.07
     Ratio
    0.07
     A
    0.07
     económicas
    0.07
    Activations Density 0.004%

    No Known Activations