© 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. 19631
    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
     hvernig
    -0.09
     how
    -0.09
     cómo
    -0.09
     handling
    -0.08
     whimsical
    -0.08
     hvordan
    -0.08
     manejo
    -0.08
     hogyan
    -0.08
    如何
    -0.08
     כיצד
    -0.08
    POSITIVE LOGITS
     przedsi
    0.15
     endeavor
    0.15
     entity
    0.14
     onderneming
    0.14
     phenomenon
    0.13
     entities
    0.13
     entidade
    0.12
    实体
    0.12
     endeavour
    0.11
     сущ
    0.11
    Activations Density 0.039%

    No Known Activations