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. 106114
    Prev
    Next
    INDEX
    Explanations

    prepositions and "ing"

    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
    .Router
    -0.08
     тех
    -0.08
    àr
    -0.08
    èy
    -0.08
     mamm
    -0.08
     هیچ
    -0.07
    rets
    -0.07
     Mam
    -0.07
     מה
    -0.07
     mett
    -0.07
    POSITIVE LOGITS
     akwai
    0.10
     yaiku
    0.10
    คือ
    0.09
     ได้แก่
    0.09
     nyaéta
    0.09
    ыў
    0.08
     isə
    0.08
     रहेका
    0.08
     todo
    0.08
    કળ
    0.08
    Activations Density 0.064%

    No Known Activations