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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106179
    Prev
    Next
    INDEX
    Explanations

    Creator/developer of something

    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
     righteousness
    -0.07
     nga
    -0.07
     diplomacy
    -0.07
     investisseurs
    -0.07
     investors
    -0.07
    consult
    -0.07
     genaue
    -0.07
    iew
    -0.07
     விர
    -0.07
     patients
    -0.07
    POSITIVE LOGITS
     знаменит
    0.10
     famous
    0.09
     famously
    0.09
    Ses
    0.09
     famed
    0.09
     प्रसिद्ध
    0.09
    Pump
    0.09
     Jeux
    0.08
     لقب
    0.08
    著
    0.08
    Activations Density 0.139%

    No Known Activations