© 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. 20690
    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
     jardins
    -0.09
    etention
    -0.08
     પ્રશ
    -0.08
     گفتگو
    -0.08
     Jardim
    -0.08
     praat
    -0.08
     intimacy
    -0.08
     appropri
    -0.08
     сериал
    -0.08
     zoning
    -0.08
    POSITIVE LOGITS
     counterfeit
    0.21
     defective
    0.19
     faulty
    0.16
     unknown
    0.15
     fraudulent
    0.15
     suspected
    0.15
     desconoc
    0.15
     সন্দ
    0.14
     adulter
    0.14
    Unknown
    0.14
    Activations Density 0.009%

    No Known Activations