© 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. 95516
    Prev
    Next
    INDEX
    Explanations

    Comparison using "than"

    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
     préférence
    -0.07
    cre
    -0.07
     contains
    -0.07
     omission
    -0.07
    abl
    -0.07
    contains
    -0.07
    નો
    -0.07
    Problem
    -0.07
    Theta
    -0.07
    ghị
    -0.07
    POSITIVE LOGITS
    -ever
    0.11
     أكثر
    0.11
     ooit
    0.10
     ATM
    0.10
     ever
    0.10
     أصبح
    0.10
     시대
    0.10
     сейчас
    0.09
     снова
    0.09
     сегодня
    0.09
    Activations Density 0.015%

    No Known Activations