Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 88263
    Prev
    Next
    INDEX
    Explanations

    celebrities, actors, stars

    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
    Manual
    -0.08
     drainage
    -0.08
    Mind
    -0.08
    Terraform
    -0.08
    Wi
    -0.08
     spool
    -0.08
    /manual
    -0.08
    dpi
    -0.07
     circumference
    -0.07
    Wizard
    -0.07
    POSITIVE LOGITS
     celebrity
    0.14
     celebrities
    0.14
     cameo
    0.12
    明星
    0.12
    Celebrity
    0.11
     guest
    0.11
     Celebrity
    0.11
    guest
    0.11
     guests
    0.10
     lineup
    0.10
    Activations Density 0.148%

    No Known Activations