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. 11-RESID-POST-AA
    6. 106311
    Prev
    Next
    INDEX
    Explanations

    boxed

    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
    Parcel
    -0.09
    parcel
    -0.09
     പാര്
    -0.09
    .desc
    -0.09
    dias
    -0.08
    .local
    -0.08
     ಲೋಕ
    -0.08
     rupa
    -0.08
     parcel
    -0.08
     cubrir
    -0.08
    POSITIVE LOGITS
    形式
    0.07
     breit
    0.07
     ber
    0.07
     schul
    0.07
     ren
    0.07
     blow
    0.07
     नी
    0.07
    制作
    0.07
     aet
    0.07
    0.07
    Activations Density 0.002%

    No Known Activations