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. 54489
    Prev
    Next
    INDEX
    Explanations

    podcast

    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
     sugar
    -0.08
     gef
    -0.07
    phants
    -0.07
     discretionary
    -0.07
    Batis
    -0.07
     paralle
    -0.07
     sugars
    -0.07
    糖
    -0.07
     الإد
    -0.07
     screws
    -0.07
    POSITIVE LOGITS
     podcast
    0.10
     podcasts
    0.10
    节目
    0.09
     듣
    0.09
     শুন
    0.09
     louder
    0.09
     audiobook
    0.09
    (audio
    0.09
     Podcasts
    0.08
     ebooks
    0.08
    Activations Density 0.006%

    No Known Activations