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. 113901
    Prev
    Next
    INDEX
    Explanations

    encounter

    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
    chim
    -0.08
    chart
    -0.07
    �
    -0.07
    fass
    -0.07
     मू
    -0.07
    prot
    -0.07
    تص
    -0.07
    audio
    -0.07
     уход
    -0.07
    ψ
    -0.07
    POSITIVE LOGITS
    遇
    0.12
     encountered
    0.11
     encounter
    0.11
     rencontré
    0.11
     сталки
    0.11
     ఎదుర
    0.11
     rencontr
    0.11
     setbacks
    0.10
     encountering
    0.10
     Encounter
    0.09
    Activations Density 0.019%

    No Known Activations