© 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. 20267
    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
    ات
    -0.08
    	at
    -0.08
     Mensen
    -0.08
    at
    -0.08
    	swap
    -0.08
     кого
    -0.08
     eindeutig
    -0.07
    .jvm
    -0.07
     사람
    -0.07
    ightly
    -0.07
    POSITIVE LOGITS
    -black
    0.15
    -coated
    0.13
    -white
    0.12
    -painted
    0.12
     black
    0.12
    -dark
    0.11
    _black
    0.11
    _WHITE
    0.11
     acabamento
    0.11
    黑
    0.10
    Activations Density 0.002%

    No Known Activations