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. 75919
    Prev
    Next
    INDEX
    Explanations

    non-English text

    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
     Residents
    -0.08
     Studium
    -0.08
     aktiv
    -0.08
     primas
    -0.08
     Shame
    -0.08
     സ്വകാര്യ
    -0.08
     menurut
    -0.08
     Estudos
    -0.08
     hindsight
    -0.07
     listas
    -0.07
    POSITIVE LOGITS
    Bay
    0.08
    cc
    0.08
    ā
    0.08
    zl
    0.08
    nh
    0.08
    oon
    0.08
    rm
    0.08
    x
    0.08
     mys
    0.08
    astos
    0.08
    Activations Density 0.404%

    No Known Activations