© 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. 22646
    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
     Centro
    -0.08
     hadde
    -0.08
     versed
    -0.07
     vamp
    -0.07
     Organización
    -0.07
     talking
    -0.07
    组织
    -0.07
     estaremos
    -0.07
    絲
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    ,const
    0.09
    ज़
    0.09
    ahui
    0.08
    unately
    0.08
     receipts
    0.08
    (ierr
    0.08
    ,date
    0.08
    �
    0.08
    abilang
    0.08
    Այ
    0.08
    Activations Density 0.000%

    No Known Activations