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. 131016
    Prev
    Next
    INDEX
    Explanations

    та

    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
    ograf
    -0.09
    omeen
    -0.08
    emist
    -0.08
    estly
    -0.08
    ebilirsiniz
    -0.08
     Alder
    -0.08
    ólogo
    -0.08
    ужден
    -0.07
    ossi
    -0.07
    ereg
    -0.07
    POSITIVE LOGITS
    ndares
    0.13
    раться
    0.12
    čí
    0.11
    цион
    0.11
    χυ
    0.10
    цыян
    0.10
    ิตย์
    0.10
    вроп
    0.10
    นด์
    0.10
    ціон
    0.10
    Activations Density 0.003%

    No Known Activations