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. 119157
    Prev
    Next
    INDEX
    Explanations

    code

    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
    komen
    -0.07
     failing
    -0.07
    ree
    -0.07
     kik
    -0.07
     equivoc
    -0.07
    ($"{
    -0.07
    met
    -0.07
     bagi
    -0.07
    yet
    -0.07
    -то
    -0.07
    POSITIVE LOGITS
    ="",
    0.09
    =None
    0.09
    ):↵
    0.09
    _percentage
    0.08
     ){↵
    0.08
    ){↵↵
    0.08
     OPTIONAL
    0.08
    Models
    0.08
    Percentage
    0.08
    ?,
    0.08
    Activations Density 0.030%

    No Known Activations