Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 111687
    Prev
    Next
    INDEX
    Explanations

    2

    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
     Manit
    -0.08
     upheld
    -0.08
     radicals
    -0.08
    WG
    -0.08
    ox
    -0.08
     radical
    -0.07
     occupational
    -0.07
     petits
    -0.07
    /is
    -0.07
     女性
    -0.07
    POSITIVE LOGITS
    .imwrite
    0.10
    .imshow
    0.09
    .imread
    0.09
    .cvt
    0.08
     distortion
    0.08
    .astype
    0.08
    astype
    0.08
    .Video
    0.08
    .rectangle
    0.08
    encv
    0.07
    Activations Density 0.002%

    No Known Activations