© 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. 44597
    Prev
    Next
    INDEX
    Explanations

    plant diseases and treatment

    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
     цяпер
    -0.08
     almacenar
    -0.08
     vibrant
    -0.08
     erectile
    -0.08
     metabolismo
    -0.08
     libido
    -0.08
    ależ
    -0.08
     auk
    -0.07
     Indy
    -0.07
    POSITIVE LOGITS
     mitigation
    0.09
     vigilance
    0.09
     zoning
    0.08
    隔
    0.07
     deployment
    0.07
     forecasting
    0.07
     protective
    0.07
     Vigil
    0.07
     timestep
    0.07
    Shade
    0.07
    Activations Density 0.003%

    No Known Activations