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. 624
    Prev
    Next
    INDEX
    Explanations

    image cropping coordinates

    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
    倡
    -0.09
     spelled
    -0.08
    纪律
    -0.08
     timely
    -0.08
    anak
    -0.08
     bisan
    -0.08
     своев
    -0.08
     Ruf
    -0.07
     reporter
    -0.07
     PEN
    -0.07
    POSITIVE LOGITS
     cropped
    0.10
    Extract
    0.09
    Thumbnail
    0.09
    Extraction
    0.09
    Adobe
    0.09
    Subtype
    0.09
    zoom
    0.08
     zoom
    0.08
    Perhaps
    0.08
     screenshot
    0.08
    Activations Density 0.001%

    No Known Activations