© 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. 23-RESID-POST-AA
    11. 50301
    Prev
    Next
    INDEX
    Explanations

    trap music production

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expr
    -0.08
    iray
    -0.08
    <Message
    -0.08
     uninstall
    -0.08
     Greenpeace
    -0.08
     suport
    -0.08
     maemo
    -0.07
    voet
    -0.07
    _mount
    -0.07
     vidéo
    -0.07
    POSITIVE LOGITS
     production
    0.17
     produção
    0.16
     producción
    0.15
     Production
    0.14
    production
    0.14
     productions
    0.14
    Production
    0.14
     produks
    0.14
     produzione
    0.13
     Auto
    0.13
    Activations Density 0.010%

    No Known Activations