© 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. 91809
    Prev
    Next
    INDEX
    Explanations

    lm

    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
     cassette
    -0.09
     glued
    -0.09
    ڼ
    -0.09
     mosque
    -0.09
     pubblic
    -0.08
     joi
    -0.08
     Numero
    -0.08
     MQTT
    -0.08
     quart
    -0.08
     mqtt
    -0.08
    POSITIVE LOGITS
     defenses
    0.08
    ခံ
    0.08
    skal
    0.08
     calculations
    0.08
    .photos
    0.08
    Requested
    0.07
     impulses
    0.07
     appet
    0.07
    AMES
    0.07
    astream
    0.07
    Activations Density 0.001%

    No Known Activations