© 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. 23-RESID-POST-AA
    11. 96357
    Prev
    Next
    INDEX
    Explanations

    UN

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toán
    -0.09
    uins
    -0.09
     ABŞ
    -0.09
    улер
    -0.09
     Ivy
    -0.09
     Алекс
    -0.08
     UL
    -0.08
     NASA
    -0.08
    ิเคราะห์
    -0.08
     homer
    -0.08
    POSITIVE LOGITS
    DP
    0.13
     Security
    0.12
     agencies
    0.12
    ESCO
    0.12
    IDO
    0.11
     Educational
    0.11
     Development
    0.11
     സെക്രട്ടറി
    0.11
     Agencies
    0.11
     Economic
    0.11
    Activations Density 0.007%

    No Known Activations