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. 131025
    Prev
    Next
    INDEX
    Explanations

    arr

    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
    CCIÓN
    -0.08
    ÇÕES
    -0.08
    elenium
    -0.08
    ného
    -0.08
    manual
    -0.08
    туру
    -0.08
    niers
    -0.08
    niú
    -0.08
    lação
    -0.08
    eldo
    -0.07
    POSITIVE LOGITS
    anca
    0.12
    uin
    0.11
    u
    0.10
    anque
    0.10
    ullar
    0.10
    astr
    0.09
    uga
    0.09
    ugas
    0.09
    ullo
    0.09
    ies
    0.09
    Activations Density 0.001%

    No Known Activations