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. 43749
    Prev
    Next
    INDEX
    Explanations

    again/more

    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
     sicer
    -0.08
     Kurz
    -0.07
     atualmente
    -0.07
     Siz
    -0.07
     Анал
    -0.07
     nis
    -0.07
     dve
    -0.07
     Existem
    -0.07
    aisen
    -0.07
     కామ
    -0.07
    POSITIVE LOGITS
     diesmal
    0.13
     erneut
    0.12
    maals
    0.11
     വീണ്ടും
    0.11
     kerran
    0.10
    again
    0.10
     again
    0.10
     снова
    0.10
    Again
    0.10
     এবার
    0.10
    Activations Density 0.083%

    No Known Activations