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. 12932
    Prev
    Next
    INDEX
    Explanations

    Least Common Multiple

    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
     abajo
    -0.08
     daudz
    -0.08
     engage
    -0.08
     opportunities
    -0.08
     premiere
    -0.08
    ưng
    -0.08
    penser
    -0.07
     comme
    -0.07
     abaixo
    -0.07
    yj
    -0.07
    POSITIVE LOGITS
    Resolution
    0.09
     Resolution
    0.09
     Anforderungen
    0.08
    .union
    0.08
     совмест
    0.08
    Resolvable
    0.08
    厘
    0.08
     Shelton
    0.07
     babu
    0.07
     요구
    0.07
    Activations Density 0.025%

    No Known Activations