© 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. 19549
    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
     if
    -0.08
    if
    -0.08
     solutions
    -0.08
     utilizando
    -0.07
    _RA
    -0.07
     solu
    -0.07
    -sol
    -0.07
    -0.07
     mathematics
    -0.07
    ytale
    -0.07
    POSITIVE LOGITS
     seen
    0.11
     prev
    0.10
     encountered
    0.10
     précédente
    0.10
    _seen
    0.10
    此前
    0.10
     vorig
    0.10
     handled
    0.10
     discovered
    0.10
    	found
    0.09
    Activations Density 0.001%
    No Known Activations