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. 98255
    Prev
    Next
    INDEX
    Explanations

    show

    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
     বু�
    -0.08
     ಮಹ
    -0.08
     pige
    -0.08
    买彩票
    -0.08
     بىر
    -0.08
     говорить
    -0.08
     qed
    -0.08
     eint
    -0.07
     parlant
    -0.07
     maduras
    -0.07
    POSITIVE LOGITS
     límite
    0.08
     ionic
    0.07
     diberikan
    0.07
     póź
    0.07
    |||
    0.07
    יני
    0.07
    yse
    0.07
     FW
    0.07
    対象
    0.06
    異
    0.06
    Activations Density 0.001%

    No Known Activations