© 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. 79145
    Prev
    Next
    INDEX
    Explanations

    user input, problem solving

    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
    িছ
    -0.09
     abbiamo
    -0.09
     we'd
    -0.08
    풍
    -0.08
     ịdị
    -0.08
     возникают
    -0.08
     subsidi
    -0.08
     anno
    -0.08
     organismo
    -0.08
     thôi
    -0.08
    POSITIVE LOGITS
     തന്റെ
    0.10
     தனது
    0.09
     తన
    0.09
    ுகிறார்
    0.08
    ிறார்
    0.08
    他的
    0.08
     himself
    0.08
     سعيد
    0.08
     earns
    0.08
     ತನ್ನ
    0.07
    Activations Density 0.065%

    No Known Activations