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. 23456
    Prev
    Next
    INDEX
    Explanations

    image composition techniques

    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
    每天
    -0.10
    领取
    -0.09
     consortium
    -0.09
     täglich
    -0.09
     phosphorus
    -0.08
     fluoride
    -0.08
    额度
    -0.08
    研发
    -0.08
     presso
    -0.08
     Vast
    -0.08
    POSITIVE LOGITS
     pleasing
    0.10
     aesthetically
    0.10
     компози
    0.09
     imagery
    0.09
     cropping
    0.09
     tension
    0.09
    .crop
    0.09
    contrast
    0.09
    (img
    0.08
     cropped
    0.08
    Activations Density 0.035%

    No Known Activations