© 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. 19-RESID-POST-AA
    11. 23111
    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
    Negative Logits
    ＊
    -0.09
    URATION
    -0.09
     THERE
    -0.09
     volg
    -0.08
     kugira
    -0.08
    URES
    -0.08
     CREATED
    -0.08
    ံု
    -0.08
     Consequently
    -0.08
    ाइज
    -0.08
    POSITIVE LOGITS
    liness
    0.20
     slate
    0.18
    -cut
    0.14
    Slate
    0.14
    room
    0.14
    ly
    0.13
     separation
    0.13
    晰
    0.12
    liest
    0.12
    lines
    0.12
    Activations Density 0.016%

    No Known Activations