© 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. 21426
    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
     segala
    -0.09
     svega
    -0.08
    _PERSON
    -0.08
     Everyone
    -0.08
    Everyone
    -0.08
     MERCHANTABILITY
    -0.08
     everyone
    -0.08
     everything
    -0.08
     edilir
    -0.07
    Jesus
    -0.07
    POSITIVE LOGITS
     cities
    0.15
     counties
    0.15
     European
    0.14
     cidades
    0.14
     европей
    0.14
     municipalities
    0.13
     Städten
    0.13
     provinces
    0.13
     southern
    0.13
     coastal
    0.13
    Activations Density 0.036%

    No Known Activations