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. 7-RESID-POST-AA
    6. 1816
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     annonser
    -0.08
     punish
    -0.08
    Advertisements
    -0.08
    pul
    -0.08
     nomor
    -0.08
    idian
    -0.07
     Präs
    -0.07
    Reporte
    -0.07
    voz
    -0.07
     punishment
    -0.07
    POSITIVE LOGITS
     Cyan
    0.08
    游戏
    0.07
     argue
    0.07
     ubi
    0.07
     Kona
    0.07
     dur
    0.07
     Xen
    0.07
    .pix
    0.07
     nc
    0.07
    0.07
    Activations Density 0.001%

    No Known Activations