© 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. 50055
    Prev
    Next
    INDEX
    Explanations

    Catalan text

    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
     Todos
    -0.10
     Cataluña
    -0.10
     Naciones
    -0.10
    inción
    -0.09
     Awọn
    -0.09
     Datos
    -0.09
    CIÓN
    -0.09
     Stato
    -0.09
    ITES
    -0.09
     Inicio
    -0.09
    POSITIVE LOGITS
     và
    0.16
     fòrça
    0.15
     dissabte
    0.15
     necessari
    0.14
     ajorn
    0.14
     correcte
    0.14
     altre
    0.13
     foguèt
    0.13
     gaire
    0.13
     financer
    0.13
    Activations Density 0.005%

    No Known Activations