© 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. 20602
    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
     We're
    -0.10
    We're
    -0.09
     You're
    -0.09
     desea
    -0.08
     we're
    -0.08
     you're
    -0.08
    You're
    -0.08
    I'm
    -0.08
     deseas
    -0.08
     I'm
    -0.08
    POSITIVE LOGITS
     isə
    0.09
    则
    0.09
    하면
    0.09
    jë
    0.09
    	where
    0.09
     however
    0.09
    حتى
    0.09
    ованием
    0.08
     donde
    0.08
    اً
    0.08
    Activations Density 0.000%

    No Known Activations