© 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. 47351
    Prev
    Next
    INDEX
    Explanations

    preliminary

    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
    empot
    -0.09
     แ
    -0.08
    なる
    -0.08
    فاعل
    -0.07
     cust
    -0.07
     מג
    -0.07
    არ�
    -0.07
    แ
    -0.07
    ಕೆ
    -0.07
     برداشت
    -0.07
    POSITIVE LOGITS
    _REQUIRE
    0.08
     wię
    0.08
     goggles
    0.08
     amus
    0.07
     luggage
    0.07
     pursuits
    0.07
     swamp
    0.07
    iforn
    0.07
     bip
    0.07
    sona
    0.07
    Activations Density 0.003%

    No Known Activations