© 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. 95541
    Prev
    Next
    INDEX
    Explanations

    command

    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
     Finals
    -0.08
     Aristotle
    -0.08
     órganos
    -0.08
     Houses
    -0.08
    arroll
    -0.07
    .Mutable
    -0.07
    abstract
    -0.07
    干部
    -0.07
    univers
    -0.07
    972
    -0.07
    POSITIVE LOGITS
     sudo
    0.14
     comando
    0.14
     comandos
    0.14
     Ubuntu
    0.13
     command
    0.13
     команд
    0.13
     commands
    0.13
     Linux
    0.13
    Linux
    0.13
    _COMMAND
    0.13
    Activations Density 0.058%

    No Known Activations