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. 53899
    Prev
    Next
    INDEX
    Explanations

    image generation prompts

    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
     electronically
    -0.09
    (transaction
    -0.08
     Goodman
    -0.08
     Mestre
    -0.07
     Loki
    -0.07
     Kirchen
    -0.07
     Sergeant
    -0.07
    gee
    -0.07
     Enlight
    -0.07
     Lern
    -0.07
    POSITIVE LOGITS
     seaside
    0.12
     beaches
    0.12
     beach
    0.11
     shoreline
    0.10
     coastline
    0.10
     dunes
    0.10
     beachfront
    0.10
     abrasion
    0.09
     praia
    0.09
     البحر
    0.09
    Activations Density 0.056%

    No Known Activations