Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58928
    Prev
    Next
    INDEX
    Explanations

    policy

    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
     MPG
    -0.09
     Cylinder
    -0.08
     Reforma
    -0.08
    _CLUSTER
    -0.08
    -conditioned
    -0.08
    	cluster
    -0.07
     Hemisphere
    -0.07
     cluster
    -0.07
     Förderung
    -0.07
     pigment
    -0.07
    POSITIVE LOGITS
    ページ
    0.11
    網站
    0.11
    を書く
    0.11
     작성
    0.11
     페이지
    0.10
    页面
    0.10
     página
    0.10
     страницу
    0.10
     website
    0.10
    頁
    0.10
    Activations Density 0.013%

    No Known Activations