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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 61064
    Prev
    Next
    INDEX
    Explanations

    Media and television

    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
     bó
    -0.08
     يحتوي
    -0.08
     fx
    -0.08
     yake
    -0.08
     инструкция
    -0.07
    intos
    -0.07
     سيارة
    -0.07
     faiz
    -0.07
     ખાન
    -0.07
     lumi
    -0.07
    POSITIVE LOGITS
    Creates
    0.09
     Prints
    0.09
     prints
    0.08
    (ed
    0.08
     budding
    0.07
     Dirty
    0.07
     pul
    0.07
    革
    0.07
     puse
    0.07
     ich
    0.07
    Activations Density 0.002%

    No Known Activations