© 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. 19-RESID-POST-AA
    11. 19373
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    's
    -0.10
    'user
    -0.09
    'univers
    -0.08
     '
    -0.08
    的不
    -0.08
     twelve
    -0.08
    'm
    -0.07
    的
    -0.07
     બધ
    -0.07
     memor
    -0.07
    POSITIVE LOGITS
     بنسبة
    0.16
     estimated
    0.14
     evidenced
    0.13
     (-
    0.13
     quantified
    0.12
     (~
    0.12
    。据
    0.12
    Estimated
    0.11
     Estimated
    0.11
     sebesar
    0.11
    Activations Density 0.053%

    No Known Activations