© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65405
    Prev
    Next
    INDEX
    Explanations

    function

    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
     Institute
    -0.08
    (par
    -0.08
     enclosing
    -0.08
     orchestr
    -0.07
     định
    -0.07
     extensive
    -0.07
     UTF
    -0.07
    -0.07
    orte
    -0.07
     ration
    -0.07
    POSITIVE LOGITS
     vengeance
    0.10
     subplot
    0.09
    _subplot
    0.09
    -vers
    0.08
     plotted
    0.08
    verters
    0.08
    _vs
    0.08
    rowth
    0.08
     vlast
    0.08
    companies
    0.08
    Activations Density 0.056%
    No Known Activations