© 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. 22354
    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
     einzigen
    -0.10
    _MINUS
    -0.09
    -End
    -0.08
     übertragen
    -0.08
     inúmeras
    -0.08
    -api
    -0.08
     sentencing
    -0.08
     miatt
    -0.08
    -two
    -0.08
    рыз
    -0.08
    POSITIVE LOGITS
     khỏe
    0.09
     responsive
    0.08
    舒服
    0.08
    offee
    0.08
     confortable
    0.08
     hambre
    0.08
    hydr
    0.08
     cold
    0.08
     warm
    0.08
     hungry
    0.08
    Activations Density 0.000%

    No Known Activations