© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 51875
    Prev
    Next
    INDEX
    Explanations

    say "wt"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    payments
    -0.09
     erected
    -0.09
     earnings
    -0.09
     hired
    -0.09
     dollars
    -0.09
     евро
    -0.09
     louer
    -0.09
     dólares
    -0.09
     Hiring
    -0.09
     incomes
    -0.09
    POSITIVE LOGITS
     wt
    0.28
    wt
    0.24
     weight
    0.24
     mass
    0.22
    weight
    0.21
    (weight
    0.21
     वजन
    0.20
    重量
    0.20
     Weight
    0.20
    Weight
    0.20
    Activations Density 0.033%

    No Known Activations