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. 44561
    Prev
    Next
    INDEX
    Explanations

    describe

    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
    want
    -0.09
     fina
    -0.08
     gle
    -0.07
     stag
    -0.07
    lal
    -0.07
     дра
    -0.07
     Sor
    -0.07
    oncé
    -0.07
     zid
    -0.07
     constr
    -0.07
    POSITIVE LOGITS
     بأنها
    0.08
     بأنه
    0.08
    Tec
    0.08
    一下
    0.08
     Vere
    0.08
    เพิ่มเติม
    0.07
    Vision
    0.07
    :none
    0.07
     kesin
    0.07
     sensation
    0.07
    Activations Density 0.063%

    No Known Activations