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. 131050
    Prev
    Next
    INDEX
    Explanations

    Turkish: definitions and planning

    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
    说道
    -0.08
     uk
    -0.08
    呢
    -0.08
     awareness
    -0.08
     ush
    -0.08
     imprisoned
    -0.08
     supone
    -0.08
    دى
    -0.07
    وبات
    -0.07
    प्त
    -0.07
    POSITIVE LOGITS
     নির
    0.13
     belir
    0.13
     Bel
    0.12
     ನಿರ
    0.11
     müəyyən
    0.10
     tay
    0.10
     నిర
    0.10
    Bel
    0.10
    ımlar
    0.10
    ıml
    0.10
    Activations Density 0.001%

    No Known Activations