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. 97971
    Prev
    Next
    INDEX
    Explanations

    нас

    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
    ைந்த
    -0.08
    نش
    -0.08
    ്റ്റ
    -0.08
    掉
    -0.08
    ண்ப
    -0.08
    mandu
    -0.08
    يط
    -0.08
    orthy
    -0.08
     regalar
    -0.08
    彩金
    -0.07
    POSITIVE LOGITS
    илия
    0.12
    илии
    0.09
    aminen
    0.09
     violência
    0.09
    uellement
    0.08
    βολ
    0.08
    illeri
    0.08
    iliy
    0.08
    armi
    0.08
    iva
    0.08
    Activations Density 0.001%

    No Known Activations