© 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. 21853
    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
     tatsäch
    -0.10
    'utiliser
    -0.09
     Luego
    -0.08
     They
    -0.08
    仍
    -0.08
    使用
    -0.08
     utilisent
    -0.08
     Use
    -0.08
     daadwerkelijk
    -0.08
     tatsächlich
    -0.08
    POSITIVE LOGITS
     approach
    0.17
    Firstly
    0.16
     Approach
    0.16
    Important
    0.15
     approche
    0.15
    Overview
    0.15
    First
    0.15
     abordagem
    0.14
    Observation
    0.14
    Appro
    0.14
    Activations Density 0.092%

    No Known Activations