© 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. 3-RESID-POST-AA
    11. 882
    Prev
    Next
    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     കൊണ്ട
    -0.08
    ово
    -0.08
     svi
    -0.07
     orange
    -0.07
     Buena
    -0.07
    čk
    -0.07
    贯
    -0.07
    Used
    -0.07
     ಮಹ
    -0.07
    Parents
    -0.07
    POSITIVE LOGITS
     Î
    0.09
    trib
    0.08
    co
    0.08
    واز
    0.08
     estr
    0.07
     trim
    0.07
     seper
    0.07
    Î
    0.07
     estiver
    0.07
    ruh
    0.07
    Activations Density 0.017%

    No Known Activations