© 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. 21522
    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
     editable
    -0.08
     strlen
    -0.08
    .Timeout
    -0.07
     crochet
    -0.07
     Tomb
    -0.07
     Waterproof
    -0.07
     recre
    -0.07
    .edit
    -0.07
    editable
    -0.07
    Editable
    -0.07
    POSITIVE LOGITS
     normalization
    0.38
    Normalization
    0.37
     Normalize
    0.35
     normalize
    0.35
    normalize
    0.34
     normalized
    0.34
    Normalize
    0.33
    normalized
    0.33
    .normalize
    0.32
    Normalized
    0.31
    Activations Density 0.010%

    No Known Activations