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. 112183
    Prev
    Next
    INDEX
    Explanations

    availability or offering

    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
     QUEST
    -0.08
     såg
    -0.08
     Modi
    -0.08
     เป
    -0.07
    λιά
    -0.07
    boek
    -0.07
     infek
    -0.07
    Bass
    -0.07
     ری
    -0.07
     diversi
    -0.07
    POSITIVE LOGITS
    _available
    0.14
     Verfügung
    0.13
    _AVAILABLE
    0.13
     tersedia
    0.13
     available
    0.13
    Available
    0.12
     disponible
    0.12
     ઉપલબ્ધ
    0.12
     disponível
    0.11
     beschikbare
    0.11
    Activations Density 0.004%

    No Known Activations