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. 130864
    Prev
    Next
    INDEX
    Explanations

    Turkish text and answers

    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
    ianik
    -0.10
    ancas
    -0.10
    ీలో
    -0.09
    ılık
    -0.09
    ანიის
    -0.09
    anca
    -0.08
    لىق
    -0.08
    ys
    -0.08
    ydessä
    -0.08
     dane
    -0.08
    POSITIVE LOGITS
    ABL
    0.10
    imat
    0.10
    aps
    0.09
    абы
    0.09
    ап
    0.09
    abla
    0.09
    Ple
    0.09
    еп
    0.09
    ip
    0.09
    abı
    0.09
    Activations Density 0.001%

    No Known Activations