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. 76024
    Prev
    Next
    INDEX
    Explanations

    use

    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
     UNIX
    -0.09
     DOS
    -0.08
     영어
    -0.08
     Laptop
    -0.08
     upbeat
    -0.08
     Lenovo
    -0.08
     Wim
    -0.07
    Typ
    -0.07
     Turbo
    -0.07
     thrilling
    -0.07
    POSITIVE LOGITS
     triangles
    0.11
     tangent
    0.10
     bridging
    0.10
     angles
    0.09
     cleverly
    0.09
    halen
    0.09
     connecting
    0.09
    Angles
    0.09
     linking
    0.09
     arcs
    0.09
    Activations Density 0.023%

    No Known Activations