© 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. 19-RESID-POST-AA
    11. 103294
    Prev
    Next
    INDEX
    Explanations

    correct

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.10
     calculate
    -0.10
     Calculates
    -0.09
     calculated
    -0.09
     calculates
    -0.09
    Calculate
    -0.09
     calcul
    -0.09
     Calculate
    -0.09
     calcula
    -0.08
     Calcul
    -0.08
    POSITIVE LOGITS
     nhọrọ
    0.13
     ընտր
    0.12
     επιλογ
    0.12
    േരള
    0.12
     առաջարկ
    0.12
    �ｲ
    0.12
    хыраара
    0.12
     微信里
    0.12
     ахада
    0.12
    րբեջ
    0.12
    Activations Density 0.003%

    No Known Activations