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. 113982
    Prev
    Next
    INDEX
    Explanations

    aging

    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
    aport
    -0.08
     uploading
    -0.07
    �
    -0.07
     confirmado
    -0.07
    ashire
    -0.07
     consecut
    -0.07
    ുണ്ട
    -0.07
     сектор
    -0.07
    이번
    -0.07
    总站
    -0.07
    POSITIVE LOGITS
     долгов
    0.14
     decay
    0.12
     timeless
    0.12
     aging
    0.12
     durability
    0.12
     langleb
    0.12
     langfrist
    0.12
     onderhoud
    0.12
    expire
    0.12
     expiration
    0.11
    Activations Density 0.068%

    No Known Activations