© 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. 20813
    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
    _DECL
    -0.08
     судь
    -0.08
     desperate
    -0.08
    Fight
    -0.07
     specializes
    -0.07
     혁
    -0.07
    strcasecmp
    -0.07
    혁
    -0.07
     innovations
    -0.07
     Doe
    -0.07
    POSITIVE LOGITS
     padding
    0.36
    	padding
    0.34
    padding
    0.34
    Padding
    0.34
     Padding
    0.33
    .padding
    0.33
    _padding
    0.32
    -padding
    0.31
    .Padding
    0.31
    _margin
    0.30
    Activations Density 0.011%

    No Known Activations