© 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. 54666
    Prev
    Next
    INDEX
    Explanations

    job appointments

    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
     penit
    -0.08
     inconven
    -0.08
     Magistr
    -0.08
     Bride
    -0.08
     inscription
    -0.08
     Appar
    -0.08
     discolor
    -0.08
    Diary
    -0.08
     chapel
    -0.08
     séance
    -0.08
    POSITIVE LOGITS
     Vertrieb
    0.10
    亚洲区
    0.10
    集团
    0.09
    sales
    0.09
     Sales
    0.09
     العالمية
    0.09
    بيعات
    0.09
     العالمي
    0.09
    营销
    0.09
     регион
    0.09
    Activations Density 0.108%

    No Known Activations