© 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. 21646
    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
     lời
    -0.09
     boredom
    -0.09
     MEMBERS
    -0.08
     ആത്മ
    -0.08
    ноним
    -0.08
     acquaintances
    -0.08
     आत्म
    -0.08
     anonim
    -0.08
     യോഗ
    -0.08
     satisf
    -0.08
    POSITIVE LOGITS
     delantero
    0.16
     rear
    0.15
    Rear
    0.15
     delanter
    0.14
    (front
    0.14
     recessed
    0.13
    rear
    0.13
     располож
    0.13
     vorne
    0.13
     installed
    0.12
    Activations Density 0.010%

    No Known Activations