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. 131054
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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
    ğimiz
    -0.11
    çiler
    -0.11
    imler
    -0.10
    ılar
    -0.10
    larımız
    -0.10
    arlar
    -0.09
    lar
    -0.09
    larni
    -0.09
    iyalar
    -0.09
    -0.09
    POSITIVE LOGITS
    ását
    0.15
    ját
    0.13
    avait
    0.12
    zeit
    0.11
    ása
    0.10
    ének
    0.10
    jára
    0.10
    ának
    0.09
    ステ
    0.09
    onj
    0.09
    Activations Density 0.004%

    No Known Activations