© 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. 3111
    Prev
    Next
    INDEX
    Explanations

    "to this day" phrase

    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
     portions
    -0.08
    (the
    -0.08
    -0.07
     rapide
    -0.07
    flower
    -0.07
     Portions
    -0.07
    tails
    -0.07
     rapides
    -0.07
     imposs
    -0.07
     bur
    -0.07
    POSITIVE LOGITS
    ång
    0.09
     Jy
    0.08
     Martial
    0.08
    Angle
    0.08
     Grie
    0.08
     ପ
    0.07
     wrought
    0.07
     Kj
    0.07
    怎么玩
    0.07
     españolas
    0.07
    Activations Density 0.000%
    No Known Activations