© 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. 19439
    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
     tricky
    -0.09
     procedure
    -0.09
     বিভ
    -0.08
     필요한
    -0.08
     dubious
    -0.08
    split
    -0.08
     peor
    -0.08
     maze
    -0.08
     difference
    -0.08
    Split
    -0.08
    POSITIVE LOGITS
     praising
    0.27
     affirmation
    0.23
     emphasizing
    0.22
     praises
    0.22
     affirm
    0.22
     reaffirm
    0.22
     celebrating
    0.22
     praise
    0.21
     celebrates
    0.21
     강조
    0.21
    Activations Density 0.120%

    No Known Activations