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. 8890
    Prev
    Next
    INDEX
    Explanations

    x

    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
     Compensation
    -0.08
    .decor
    -0.08
     Ethan
    -0.07
     blocker
    -0.07
     folding
    -0.07
    ाकार
    -0.07
    ೃ
    -0.07
    此同时
    -0.07
    (Change
    -0.07
    isinin
    -0.07
    POSITIVE LOGITS
    864
    0.08
    �
    0.08
     Venetian
    0.08
    fre
    0.08
     mou
    0.08
    wią
    0.08
    04
    0.08
     ICO
    0.07
    ৮
    0.07
    02
    0.07
    Activations Density 0.003%

    No Known Activations