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. 111816
    Prev
    Next
    INDEX
    Explanations

    The word "lose"

    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
     reaf
    -0.08
     insurance
    -0.08
     mistaken
    -0.08
     Insurance
    -0.07
     dece
    -0.07
     выб
    -0.07
     ira
    -0.07
     کری
    -0.07
    AFP
    -0.07
     uterus
    -0.07
    POSITIVE LOGITS
     детал
    0.09
     nuance
    0.09
     Details
    0.09
     detalles
    0.08
    细
    0.08
    zieć
    0.08
     nuances
    0.08
    .details
    0.08
     details
    0.08
    細
    0.08
    Activations Density 0.009%

    No Known Activations