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. 112834
    Prev
    Next
    INDEX
    Explanations

    ly

    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
     objects
    -0.08
     તેમાં
    -0.08
    )(
    -0.07
     SOL
    -0.07
    ATAL
    -0.07
    entlichen
    -0.07
    oled
    -0.07
     validity
    -0.07
    (serializer
    -0.07
    Or
    -0.07
    POSITIVE LOGITS
     proté
    0.09
     knack
    0.08
     shortlisted
    0.08
     feta
    0.08
     отзывы
    0.08
    making
    0.08
     interview
    0.08
     proactive
    0.08
     kios
    0.08
     cuide
    0.08
    Activations Density 0.002%

    No Known Activations