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. 102963
    Prev
    Next
    INDEX
    Explanations

    ros

    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
     rand
    -0.08
     reç
    -0.08
     disruptive
    -0.07
     tani
    -0.07
     message
    -0.07
    ideen
    -0.07
     lev
    -0.07
    terness
    -0.07
    (validate
    -0.07
    validate
    -0.07
    POSITIVE LOGITS
    .Description
    0.08
    ালো
    0.08
     Eleanor
    0.08
    .Me
    0.08
    illing
    0.08
     nutrition
    0.08
     Elizabeth
    0.08
     profiss
    0.08
    .Stage
    0.08
    Elizabeth
    0.07
    Activations Density 0.002%

    No Known Activations