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. 106328
    Prev
    Next
    INDEX
    Explanations

    $"

    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
    .ser
    -0.08
     mistake
    -0.08
    _detect
    -0.08
    _port
    -0.08
    .detect
    -0.08
     errores
    -0.08
    aly
    -0.08
    fas
    -0.08
    defaults
    -0.08
    મેન્ટ
    -0.08
    POSITIVE LOGITS
    289
    0.07
     secretario
    0.07
     thong
    0.07
     thức
    0.07
     Uniti
    0.07
     residential
    0.07
     MEMBERS
    0.07
     Assembly
    0.07
     laws
    0.07
     Sheets
    0.07
    Activations Density 0.004%

    No Known Activations