© 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. 99164
    Prev
    Next
    INDEX
    Explanations

    numbers and counting

    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
     (
    -0.08
    (dat
    -0.07
     is
    -0.07
    都有
    -0.07
    满足
    -0.07
    订
    -0.07
     """
    -0.07
    (
    -0.07
     /
    -0.07
     satisfies
    -0.07
    POSITIVE LOGITS
     остальных
    0.10
     remarque
    0.09
     restantes
    0.09
     unaffected
    0.09
     strolling
    0.09
     остальные
    0.09
    -empty
    0.09
     øvr
    0.09
    irg
    0.09
    -serif
    0.09
    Activations Density 0.220%

    No Known Activations