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. 9138
    Prev
    Next
    INDEX
    Explanations

    got

    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
    -0.07
    onstruk
    -0.07
    ikor
    -0.07
    aktor
    -0.07
    ikana
    -0.07
    avan
    -0.07
    igg
    -0.07
    :url
    -0.07
     Scotts
    -0.07
    "}),↵
    -0.07
    POSITIVE LOGITS
     jail
    0.08
     предыдущ
    0.08
     cease
    0.08
     conn
    0.07
     defer
    0.07
     السابقة
    0.07
     전달
    0.07
     Preschool
    0.07
    0.07
     falar
    0.07
    Activations Density 0.002%

    No Known Activations