© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 109946
    Prev
    Next
    INDEX
    Explanations

    academic articles

    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
    Negative Logits
    。不
    -0.08
     forums
    -0.08
    ;</
    -0.08
     bookings
    -0.08
    其中
    -0.08
    。在
    -0.08
     '''
↵
    -0.08
     '''↵
    -0.08
     rospy
    -0.07
    。如果
    -0.07
    POSITIVE LOGITS
     hepatitis
    0.08
    Structural
    0.08
    Validated
    0.08
    иваем
    0.08
    DEPEND
    0.08
    Novel
    0.08
    Coronavirus
    0.07
    also
    0.07
     champagne
    0.07
     Fif
    0.07
    Activations Density 0.021%

    No Known Activations