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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 19244
    Prev
    Next
    INDEX
    Explanations

    Height

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plagiarism
    -0.11
    多人
    -0.09
    ifax
    -0.09
    群
    -0.08
     plethora
    -0.08
     rally
    -0.08
    neighbors
    -0.08
    名单
    -0.08
     Alphabet
    -0.07
     иқтис
    -0.07
    POSITIVE LOGITS
    高さ
    0.14
     height
    0.12
    HEIGHT
    0.12
     layers
    0.12
     hauteur
    0.11
     thickness
    0.11
     Height
    0.11
     HEIGHT
    0.11
    Height
    0.11
    -height
    0.11
    Activations Density 0.027%

    No Known Activations