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. 23-RESID-POST-AA
    6. 98627
    Prev
    Next
    INDEX
    Explanations

    Re

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zụ
    -0.09
    ныя
    -0.08
    ীয়া
    -0.08
    нае
    -0.07
    кая
    -0.07
    иа
    -0.07
     tooling
    -0.07
     какое
    -0.07
     ansonsten
    -0.07
    azụ
    -0.07
    POSITIVE LOGITS
     Mister
    0.09
    friger
    0.09
     renter
    0.08
     Bihar
    0.08
    wanda
    0.08
    irat
    0.08
    inker
    0.08
    epers
    0.08
    .rf
    0.07
    EFR
    0.07
    Activations Density 0.000%

    No Known Activations