© 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. 108810
    Prev
    Next
    INDEX
    Explanations

    math and coding

    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
    AW
    -0.08
     Partnership
    -0.08
     Loft
    -0.07
    _Move
    -0.07
    _Request
    -0.07
     Edit
    -0.07
    e
    -0.07
     Change
    -0.07
    _Value
    -0.07
     hamburg
    -0.06
    POSITIVE LOGITS
     glean
    0.10
     المص
    0.10
     extracted
    0.10
     inferred
    0.10
     derived
    0.10
     arising
    0.09
     اصط
    0.09
    ifiée
    0.09
    derived
    0.09
    ركات
    0.09
    Activations Density 0.295%

    No Known Activations