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. 102787
    Prev
    Next
    INDEX
    Explanations

    style

    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
     mentions
    -0.08
     politically
    -0.08
    -intensive
    -0.08
     குறித்து
    -0.08
     లో
    -0.07
    ירות
    -0.07
     obviously
    -0.07
     ની
    -0.07
     కు
    -0.07
    -aware
    -0.07
    POSITIVE LOGITS
     pili
    0.08
     Glenn
    0.08
    ээр
    0.08
     pep
    0.07
    impi
    0.07
    、《
    0.07
     pancakes
    0.07
    aher
    0.07
    .Require
    0.07
     Sacred
    0.07
    Activations Density 0.014%

    No Known Activations