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. 582
    Prev
    Next
    INDEX
    Explanations

    likely

    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
    �
    -0.08
     asc
    -0.08
     hinaus
    -0.07
     обознач
    -0.07
    栏
    -0.07
    varna
    -0.07
     propagated
    -0.07
    атков
    -0.07
    äl
    -0.07
     Esp
    -0.07
    POSITIVE LOGITS
    ที่จะ
    0.10
    hood
    0.08
    收到
    0.08
     تساعد
    0.07
    Rice
    0.07
    _false
    0.07
     النجاح
    0.07
    idm
    0.07
     Roe
    0.07
     العالية
    0.07
    Activations Density 0.022%

    No Known Activations