© 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. 3-RESID-POST-AA
    11. 2587
    Prev
    Next
    INDEX
    Explanations

    dés

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     complication
    -0.08
     nela
    -0.08
     nessa
    -0.08
     nesta
    -0.08
    �
    -0.08
     intense
    -0.07
    ,pos
    -0.07
     పరిశ
    -0.07
    の場合
    -0.07
     VIII
    -0.07
    POSITIVE LOGITS
     Qua
    0.08
     qp
    0.08
     bav
    0.08
     bestehen
    0.07
    گیر
    0.07
    chid
    0.07
    haus
    0.07
    Han
    0.07
    sss
    0.07
     barg
    0.07
    Activations Density 0.000%

    No Known Activations