© 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. 110162
    Prev
    Next
    INDEX
    Explanations

    travel departure

    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
    -0.07
     깨
    -0.07
     تقدم
    -0.07
    积
    -0.07
     대해서
    -0.07
    ills
    -0.07
     colt
    -0.07
     Ill
    -0.07
    }[
    -0.07
     있게
    -0.06
    POSITIVE LOGITS
     embarking
    0.12
    出去
    0.11
     khỏi
    0.11
     निकल
    0.10
     embark
    0.10
    Departure
    0.10
     vertrekken
    0.10
     vertrek
    0.09
     departing
    0.09
     departure
    0.09
    Activations Density 0.052%
    No Known Activations