© 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. 21723
    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
     банки
    -0.09
     reused
    -0.08
    二等奖
    -0.08
     healed
    -0.08
     solved
    -0.08
     ಬ್ಯಾಂ
    -0.08
    unfinished
    -0.08
    絲襪
    -0.08
     maslahat
    -0.08
    .extensions
    -0.08
    POSITIVE LOGITS
     decline
    0.24
     deterioration
    0.21
     declines
    0.18
     progression
    0.17
     declining
    0.16
     deterior
    0.16
    Decl
    0.16
     Decl
    0.16
     degradation
    0.15
     ухуд
    0.15
    Activations Density 0.006%

    No Known Activations