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. 97116
    Prev
    Next
    INDEX
    Explanations

    say "import"

    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
     dowam
    -0.09
    lọwọ
    -0.09
    kmale
    -0.09
    �്ച
    -0.08
     paano
    -0.08
     mfano
    -0.08
     ullu
    -0.08
     ntxiv
    -0.08
     saý
    -0.08
    ί
    -0.08
    POSITIVE LOGITS
    'use
    0.20
    "use
    0.19
    'user
    0.13
    using
    0.12
    #pragma
    0.12
    #ifndef
    0.11
    /*!↵
    0.11
    "user
    0.11
    """
    0.11
    /*!
    0.11
    Activations Density 0.006%

    No Known Activations