© 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. 47779
    Prev
    Next
    INDEX
    Explanations

    Natural log computations

    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
    krat
    -0.08
    ities
    -0.08
    庭
    -0.08
    ot
    -0.07
    inat
    -0.07
    sei
    -0.07
     AUS
    -0.07
     sever
    -0.07
    seo
    -0.07
    atche
    -0.07
    POSITIVE LOGITS
     resa
    0.08
    294
    0.08
     Individ
    0.08
     conocer
    0.07
    еша
    0.07
    .Res
    0.07
     λύ
    0.07
     הגד
    0.07
    лага
    0.07
    ψει
    0.07
    Activations Density 0.003%

    No Known Activations