© 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 EvalsExportsAPI 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. 19801
    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
     continuamente
    -0.09
     constantemente
    -0.08
     actief
    -0.08
     complaints
    -0.08
    ambres
    -0.08
     constamment
    -0.08
     agré
    -0.08
     diversas
    -0.08
     requester
    -0.08
     vorhand
    -0.08
    POSITIVE LOGITS
     pivotal
    0.32
     milestone
    0.31
     milestones
    0.26
     landmark
    0.24
     watershed
    0.22
     seminal
    0.20
     significant
    0.20
     marking
    0.20
     monumental
    0.19
     marks
    0.19
    Activations Density 0.094%

    No Known Activations