© 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. 22986
    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
     plank
    -0.08
     physicians
    -0.08
    Doctors
    -0.08
     salads
    -0.08
     beers
    -0.08
     médecins
    -0.08
     drowning
    -0.08
     aspirin
    -0.08
    ганда
    -0.07
     beat
    -0.07
    POSITIVE LOGITS
    狐狸
    0.20
     fox
    0.20
     Fox
    0.16
    狐
    0.16
    fox
    0.15
    Fox
    0.14
    xf
    0.13
     FOX
    0.12
    FOX
    0.12
     sly
    0.12
    Activations Density 0.014%

    No Known Activations