© 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. 1226
    Prev
    Next
    INDEX
    Explanations

    picture

    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
    inite
    -0.09
     rell
    -0.08
     vac
    -0.08
     shy
    -0.08
     festen
    -0.08
     Vegetarian
    -0.08
     aki
    -0.08
     chut
    -0.07
    ઈ
    -0.07
    tong
    -0.07
    POSITIVE LOGITS
     deserving
    0.07
    {|
    0.07
     टी
    0.07
     oversee
    0.07
    ij
    0.07
     mosa
    0.07
     규모
    0.07
     TOUCH
    0.07
    0.07
     overseeing
    0.07
    Activations Density 0.012%
    No Known Activations