© 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. 52272
    Prev
    Next
    INDEX
    Explanations

    invasive plant species

    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
     palest
    -0.08
     impotence
    -0.08
     innocence
    -0.08
    -0.08
    Pilot
    -0.08
     piace
    -0.08
    iper
    -0.07
    वाही
    -0.07
     Palestinian
    -0.07
     Pilot
    -0.07
    POSITIVE LOGITS
    夜
    0.08
     Smooth
    0.08
     Kud
    0.08
     夜
    0.08
     NIGHT
    0.08
     leafy
    0.07
    _CHAT
    0.07
     hierarchical
    0.07
     M
    0.07
    osion
    0.07
    Activations Density 0.001%
    No Known Activations