© 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. 54614
    Prev
    Next
    INDEX
    Explanations

    GPT token limits

    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
    NOS
    -0.08
    Approve
    -0.08
    st
    -0.08
    .In
    -0.08
    no
    -0.08
    Authority
    -0.08
    wanted
    -0.08
     roadside
    -0.07
     അംഗ
    -0.07
    reto
    -0.07
    POSITIVE LOGITS
     тысячи
    0.09
     Millionen
    0.09
     linguistic
    0.09
     Keskimäär
    0.09
     roughly
    0.09
     लाख
    0.09
     synonymous
    0.09
     advers
    0.09
     લાખ
    0.09
     હજાર
    0.09
    Activations Density 0.006%

    No Known Activations