© 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. 23-RESID-POST-AA
    11. 52165
    Prev
    Next
    INDEX
    Explanations

    fall/falls

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     lying
    -0.10
     belonging
    -0.09
     Up
    -0.09
     standing
    -0.09
     entering
    -0.09
     Going
    -0.09
     Coming
    -0.09
     stance
    -0.09
     overflowing
    -0.09
     going
    -0.08
    POSITIVE LOGITS
     square
    0.13
     prey
    0.12
     short
    0.11
    square
    0.11
    于
    0.11
     just
    0.10
     Square
    0.10
    Square
    0.10
     neatly
    0.10
    -square
    0.10
    Activations Density 0.025%

    No Known Activations