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. 43877
    Prev
    Next
    INDEX
    Explanations

    city tourist attractions

    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
     repr
    -0.09
    томат
    -0.08
     independent
    -0.08
     valide
    -0.08
     Independent
    -0.08
     kyse
    -0.08
     Jared
    -0.08
     commerce
    -0.08
     fal
    -0.08
     modific
    -0.07
    POSITIVE LOGITS
     waterfront
    0.10
    .chart
    0.08
     perspekt
    0.08
    mah
    0.08
     cumul
    0.08
     uitzicht
    0.08
    ıt
    0.08
    -divider
    0.07
    observable
    0.07
     mirrors
    0.07
    Activations Density 0.005%

    No Known Activations