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. 98471
    Prev
    Next
    INDEX
    Explanations

    Spanish -ir verbs

    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
    ow
    -0.08
    ché
    -0.07
     ci
    -0.07
     zast
    -0.07
    owi
    -0.07
    me
    -0.07
    ово
    -0.07
    ohon
    -0.07
    chè
    -0.07
    elin
    -0.07
    POSITIVE LOGITS
    ía
    0.14
    ia
    0.14
    ÍA
    0.12
    ían
    0.10
    ੀਆ
    0.10
    िया
    0.09
    IA
    0.09
    �a
    0.08
    ait
    0.08
    ría
    0.08
    Activations Density 0.001%

    No Known Activations