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. 112900
    Prev
    Next
    INDEX
    Explanations

    composition

    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
     इलाज
    -0.08
    Ken
    -0.07
    Fuse
    -0.07
    áveis
    -0.07
     piem
    -0.07
    ios
    -0.07
    vera
    -0.07
     얼마
    -0.07
    abric
    -0.07
     rover
    -0.07
    POSITIVE LOGITS
     תוך
    0.09
     وكانت
    0.08
     असून
    0.08
    이며
    0.08
    ,自
    0.08
     minus
    0.07
     kanthi
    0.07
     într
    0.07
     ומה
    0.07
     erstmals
    0.07
    Activations Density 0.010%

    No Known Activations