© 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. 20754
    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
    _subplot
    -0.11
    Bedrooms
    -0.10
    subplot
    -0.09
     площ
    -0.09
     subplot
    -0.09
    plot
    -0.09
     jardim
    -0.08
     plots
    -0.08
    Plots
    -0.08
     gestalten
    -0.08
    POSITIVE LOGITS
     token
    0.32
    _token
    0.32
    Token
    0.31
     tokens
    0.31
    	token
    0.31
    token
    0.30
    _TOKEN
    0.30
     Token
    0.29
    .token
    0.29
     ток
    0.29
    Activations Density 0.010%

    No Known Activations