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. 65500
    Prev
    Next
    INDEX
    Explanations

    train

    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
     Ano
    -0.09
     ano
    -0.09
    tributions
    -0.08
     modulo
    -0.08
     disf
    -0.08
     culin
    -0.08
    -bootstrap
    -0.08
     thereby
    -0.08
     الاجتماعي
    -0.07
    ימון
    -0.07
    POSITIVE LOGITS
    驶
    0.12
    铁路
    0.11
     railway
    0.09
     headlights
    0.09
     Railway
    0.09
     rijdt
    0.09
    Length
    0.09
     fährt
    0.08
     Rail
    0.08
    Passenger
    0.08
    Activations Density 0.010%

    No Known Activations