© 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. 99663
    Prev
    Next
    INDEX
    Explanations

    expand

    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
    awasan
    -0.09
     wandering
    -0.08
     starving
    -0.08
     encant
    -0.08
    uições
    -0.08
    طلاق
    -0.08
     cuidad
    -0.08
     ఎదుర
    -0.08
    נועה
    -0.08
     migrating
    -0.07
    POSITIVE LOGITS
    隐藏
    0.11
     disclosures
    0.10
     revealed
    0.10
     reveals
    0.10
     скры
    0.10
     reveal
    0.10
    阅读全文
    0.09
     disclosure
    0.09
    Reveal
    0.09
     concealed
    0.09
    Activations Density 0.009%

    No Known Activations