Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 112067
    Prev
    Next
    INDEX
    Explanations

    computer ports and services

    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
    鉴
    -0.08
     పర
    -0.08
    浓
    -0.08
     sir
    -0.08
     lim
    -0.08
    计
    -0.08
     Bombe
    -0.08
    _counts
    -0.07
    惯
    -0.07
    فية
    -0.07
    POSITIVE LOGITS
     auditorium
    0.08
    \Type
    0.08
     categoria
    0.08
    ruary
    0.08
     Ell
    0.08
    èche
    0.08
    rage
    0.08
    pli
    0.08
     Wing
    0.08
     voru
    0.08
    Activations Density 0.002%

    No Known Activations