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. 15-RESID-POST-AA
    6. 19102
    Prev
    Next
    INDEX
    Explanations

    negation

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ительство
    -0.09
    ండి
    -0.09
    инки
    -0.08
     känner
    -0.08
     Honduras
    -0.08
     giống
    -0.08
    инка
    -0.08
     önüm
    -0.08
    もっと
    -0.08
    .Virtual
    -0.07
    POSITIVE LOGITS
     predicate
    0.12
     neg
    0.11
    predicate
    0.11
     negate
    0.10
     predicates
    0.10
    compl
    0.10
     complements
    0.10
    _neg
    0.09
     contrap
    0.09
     Predicate
    0.09
    Activations Density 0.019%

    No Known Activations