© 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. 68571
    Prev
    Next
    INDEX
    Explanations

    ge

    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
     lineage
    -0.10
     notes
    -0.08
     SIG
    -0.07
     records
    -0.07
     persec
    -0.07
     märk
    -0.07
    .clear
    -0.07
    .Status
    -0.07
    ાઇલ
    -0.07
    कॉ
    -0.07
    POSITIVE LOGITS
     豪
    0.09
     提
    0.09
     禁
    0.09
     지급
    0.09
     淘
    0.09
     साबित
    0.08
     Thai
    0.08
     বক্তব্য
    0.08
     泰
    0.08
    集团
    0.08
    Activations Density 0.030%

    No Known Activations