© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 30428
    Prev
    Next
    INDEX
    Explanations

    navigation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '"'
    -0.08
     Barclays
    -0.08
    Entidad
    -0.08
    .Usuario
    -0.08
    جير
    -0.08
     Señor
    -0.07
     Ciencia
    -0.07
    �
    -0.07
    (cors
    -0.07
     parten
    -0.07
    POSITIVE LOGITS
    /navigation
    0.10
    buttons
    0.10
    navigation
    0.10
    views
    0.10
    _navigation
    0.09
    -navigation
    0.09
    Navigation
    0.09
     navigation
    0.09
    .navigation
    0.09
     Navigation
    0.09
    Activations Density 0.008%

    No Known Activations