© 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. 15-RESID-POST-AA
    11. 16592
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     старт
    -0.09
     腾
    -0.09
     pronounced
    -0.08
    уну
    -0.08
     loro
    -0.08
    登陆
    -0.08
     龙头
    -0.08
     cambio
    -0.08
     ลูก
    -0.08
     trasfer
    -0.08
    POSITIVE LOGITS
    Detailed
    0.09
     We'll
    0.09
    assistant
    0.09
     déta
    0.08
    <|message|>
    0.08
    Explain
    0.08
    english
    0.08
     Detailed
    0.08
     explaining
    0.08
     Understanding
    0.08
    Activations Density 0.041%

    No Known Activations