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. 53216
    Prev
    Next
    INDEX
    Explanations

    86

    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
     chim
    -0.07
     endorsed
    -0.07
     chest
    -0.07
     তাক
    -0.07
    Kar
    -0.07
    sprech
    -0.07
     Palmas
    -0.07
    ాప్
    -0.07
    bou
    -0.07
     asseg
    -0.07
    POSITIVE LOGITS
    是一
    0.10
    数据显示
    0.09
     
    0.09
    Es
    0.08
    ILENAME
    0.08
    ാൻ
    0.08
    人在
    0.08
     merupakan
    0.08
    曾
    0.08
     לי
    0.08
    Activations Density 0.161%

    No Known Activations