Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 44009
    Prev
    Next
    INDEX
    Explanations

    Resource optimization math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bord
    -0.07
    ceso
    -0.07
    ужден
    -0.07
    ampus
    -0.07
    Header
    -0.07
    _usr
    -0.07
    =subprocess
    -0.07
    ภัย
    -0.07
    اتی
    -0.07
    Caption
    -0.06
    POSITIVE LOGITS
     Konzentr
    0.09
     കേ
    0.09
    hnten
    0.08
     manière
    0.08
     Antoine
    0.08
     нанос
    0.08
     centimeter
    0.08
     gange
    0.08
     jungle
    0.08
    ργ
    0.08
    Activations Density 0.002%

    No Known Activations