© 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. 23-RESID-POST-AA
    11. 97789
    Prev
    Next
    INDEX
    Explanations

    ford

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <Class
    -0.09
    等奖
    -0.08
    <Account
    -0.08
    <Select
    -0.08
     alloy
    -0.08
    <<(
    -0.08
     financing
    -0.08
     esfuerzos
    -0.08
    <Contact
    -0.08
    <Group
    -0.08
    POSITIVE LOGITS
     نفسه
    0.10
     countryside
    0.09
     نفسها
    0.09
     Farmers
    0.09
     offers
    0.09
     중심
    0.09
     WOW
    0.08
     bietet
    0.08
     Glow
    0.08
     sentrum
    0.08
    Activations Density 0.011%

    No Known Activations