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. 49179
    Prev
    Next
    INDEX
    Explanations

    Narrowing

    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
     CSS
    -0.08
     outsider
    -0.08
     cows
    -0.07
     Sparrow
    -0.07
    _cookie
    -0.07
     shift
    -0.07
     irrespons
    -0.07
     cheat
    -0.07
     outsiders
    -0.07
     cheating
    -0.07
    POSITIVE LOGITS
     sten
    0.12
     blockage
    0.12
     ducts
    0.12
     tubing
    0.11
     junction
    0.11
     tunnels
    0.11
     tube
    0.11
     bott
    0.11
     conduit
    0.11
     clogged
    0.10
    Activations Density 0.029%

    No Known Activations