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. 65694
    Prev
    Next
    INDEX
    Explanations

    Math equations

    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
     innumer
    -0.08
     ಶ
    -0.07
     cloud
    -0.07
     Himalayan
    -0.07
     ದೃ
    -0.07
     श
    -0.07
     ಪ್ರತ
    -0.07
    मेंट
    -0.07
     chino
    -0.07
     shrimp
    -0.06
    POSITIVE LOGITS
    .coe
    0.09
    (coeff
    0.09
     PRESS
    0.08
     coeff
    0.08
    keh
    0.08
     Stevenson
    0.08
     ә
    0.08
     PES
    0.08
    €‰
    0.08
     Carroll
    0.08
    Activations Density 0.028%

    No Known Activations