© 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. 19677
    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
     무엇
    -0.09
     אנו
    -0.08
    what
    -0.08
     what's
    -0.08
     mitä
    -0.08
    concile
    -0.08
     sitä
    -0.07
     ζη
    -0.07
     אנחנו
    -0.07
     olivat
    -0.07
    POSITIVE LOGITS
     alters
    0.11
     cambiar
    0.11
     ofrecer
    0.11
     sweeter
    0.11
     alterar
    0.11
     ofrece
    0.11
     smoother
    0.11
     warmer
    0.11
     alter
    0.10
     ofrecen
    0.10
    Activations Density 0.011%

    No Known Activations