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. 88224
    Prev
    Next
    INDEX
    Explanations

    matching games

    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
    utzutage
    -0.09
    erso
    -0.08
    icionado
    -0.08
     Electric
    -0.08
     мощности
    -0.08
     خطاب
    -0.08
    ివ
    -0.08
    Muh
    -0.08
    ød
    -0.08
    -resistant
    -0.08
    POSITIVE LOGITS
     pairs
    0.13
     pair
    0.12
    Pair
    0.12
    Pairs
    0.12
    pair
    0.11
    _pairs
    0.11
    _pair
    0.10
     parejas
    0.10
    _PAIR
    0.10
     Pair
    0.10
    Activations Density 0.006%

    No Known Activations