© 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. 21788
    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
     conflitos
    -0.08
    ாளர்
    -0.08
     conflicto
    -0.08
     conflictos
    -0.07
     सकारात्मक
    -0.07
     Rover
    -0.07
     DNS
    -0.07
     conflicts
    -0.07
     usc
    -0.07
     Traffic
    -0.07
    POSITIVE LOGITS
     холод
    0.15
     chilly
    0.14
    寒
    0.14
     temperatures
    0.14
     colder
    0.14
     fría
    0.13
     chills
    0.13
     cold
    0.13
     chill
    0.13
    空气
    0.12
    Activations Density 0.024%

    No Known Activations