Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12533
    Prev
    Next
    INDEX
    Explanations

    Device touch/press interactions

    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
     مذ
    -0.08
    bases
    -0.08
     disgust
    -0.08
     النقل
    -0.07
    utsi
    -0.07
     సామ
    -0.07
     preju
    -0.07
    vehicles
    -0.07
     depicting
    -0.07
    auction
    -0.07
    POSITIVE LOGITS
     prolonged
    0.09
     LEDs
    0.09
     Longer
    0.09
    _gpio
    0.08
     gpio
    0.08
     Hyatt
    0.08
     langdur
    0.08
     durée
    0.08
     powering
    0.08
    ẹrẹ
    0.08
    Activations Density 0.003%

    No Known Activations