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. 55361
    Prev
    Next
    INDEX
    Explanations

    Allied

    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
     formulier
    -0.08
    纽
    -0.08
     negosyo
    -0.08
    NFL
    -0.08
    ,array
    -0.07
    dots
    -0.07
     bikin
    -0.07
    ్చ
    -0.07
     Twain
    -0.07
    ต
    -0.07
    POSITIVE LOGITS
     પાસે
    0.08
    وقف
    0.07
     advancements
    0.07
     अभिय
    0.07
     regroup
    0.07
    akers
    0.07
    aking
    0.07
     nations
    0.07
     पक्ष
    0.07
     تحقيق
    0.07
    Activations Density 0.009%

    No Known Activations