© 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. 18529
    Prev
    Next
    INDEX
    Explanations

    jealousy, envy

    np_max-act-logits · gemini-2.0-flash
    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
     discovery
    -0.14
     discovered
    -0.12
    Discovery
    -0.11
     detection
    -0.11
     descoberta
    -0.11
     ontdek
    -0.10
     discoveries
    -0.10
     découverte
    -0.10
     descubierto
    -0.10
     கண்ட
    -0.10
    POSITIVE LOGITS
     jealousy
    0.35
     jealous
    0.31
    �
    0.29
     envy
    0.25
     Je
    0.23
     jalo
    0.23
    Je
    0.21
     beneid
    0.21
     jal
    0.21
     neid
    0.20
    Activations Density 0.016%

    No Known Activations