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. 61067
    Prev
    Next
    INDEX
    Explanations

    version

    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
     hood
    -0.08
    _types
    -0.08
    ovic
    -0.08
     Types
    -0.08
     maravil
    -0.08
    響
    -0.07
     Nazir
    -0.07
    跨
    -0.07
     conn
    -0.07
    _names
    -0.07
    POSITIVE LOGITS
     специально
    0.09
    (super
    0.08
     hver
    0.08
     boven
    0.08
     сох
    0.08
     tomate
    0.08
     Andres
    0.08
     сер
    0.07
     организа
    0.07
    
    ↵
    0.07
    Activations Density 0.010%

    No Known Activations