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. 24347
    Prev
    Next
    INDEX
    Explanations

    printing

    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
     ICollection
    -0.08
     graz
    -0.08
     spectator
    -0.08
     swimmer
    -0.08
     restrictive
    -0.08
     Jel
    -0.07
     Namespace
    -0.07
    Swimming
    -0.07
     Structured
    -0.07
     PCA
    -0.07
    POSITIVE LOGITS
     dissemin
    0.11
    传播
    0.11
     Gutenberg
    0.10
     dissemination
    0.10
    字号
    0.10
    出版
    0.10
     pamph
    0.09
     текста
    0.09
     printing
    0.09
     Disse
    0.09
    Activations Density 0.007%

    No Known Activations