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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 43490
    Prev
    Next
    INDEX
    Explanations

    Two possible

    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
     testified
    -0.08
     halaman
    -0.07
     quels
    -0.07
    _browser
    -0.07
     day
    -0.07
    page
    -0.07
     weighted
    -0.07
     Kendrick
    -0.07
    high
    -0.07
    klan
    -0.07
    POSITIVE LOGITS
     Depending
    0.09
     dependendo
    0.09
     halves
    0.09
     depending
    0.08
     dependiendo
    0.08
     abụọ
    0.08
    solutions
    0.08
     CRS
    0.08
    -thirds
    0.08
     acos
    0.08
    Activations Density 0.038%

    No Known Activations