© 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 EvalsExportsAPI 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. 19861
    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
    ondere
    -0.08
    .deck
    -0.08
    െയുള്ള
    -0.07
     Tổng
    -0.07
     trendy
    -0.07
    avorable
    -0.07
    oben
    -0.07
     denomin
    -0.07
    هان
    -0.07
     negatieve
    -0.07
    POSITIVE LOGITS
    😭
    0.17
    哭
    0.16
     lágrimas
    0.16
     cried
    0.15
     crying
    0.15
    涙
    0.14
     sorrow
    0.13
     llor
    0.13
     sadness
    0.13
     tears
    0.12
    Activations Density 0.025%

    No Known Activations