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. 53928
    Prev
    Next
    INDEX
    Explanations

    thrust

    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
     incubation
    -0.08
    .unsubscribe
    -0.08
     constellation
    -0.07
    .sap
    -0.07
    const
    -0.07
     counterparts
    -0.07
     incub
    -0.07
     padrões
    -0.07
     motivation
    -0.07
    .std
    -0.07
    POSITIVE LOGITS
     Accommodation
    0.08
     sideways
    0.08
     bienes
    0.08
    .Wrap
    0.08
    نده
    0.08
     draait
    0.08
     Compress
    0.08
     Fault
    0.08
     desplaz
    0.08
     Millet
    0.08
    Activations Density 0.002%

    No Known Activations