© 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. 16495
    Prev
    Next
    INDEX
    Explanations

    ChatGPT system messages

    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
     lohnt
    -0.09
    .mapreduce
    -0.08
    .bukkit
    -0.08
    的钱
    -0.08
     desto
    -0.08
     impacted
    -0.08
     influ
    -0.08
     stagn
    -0.08
    .Bitmap
    -0.08
     halves
    -0.07
    POSITIVE LOGITS
     prioridad
    0.11
     prioritize
    0.11
    Always
    0.10
    输出
    0.10
     selalu
    0.10
     obedience
    0.10
     omn
    0.10
     stets
    0.10
     ALWAYS
    0.09
     priorit
    0.09
    Activations Density 0.013%

    No Known Activations