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. 65815
    Prev
    Next
    INDEX
    Explanations

    طور

    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
    stuff
    -0.08
    idi
    -0.07
    embership
    -0.07
    namespace
    -0.07
     आवाज
    -0.07
    textbox
    -0.07
    idzi
    -0.07
     కు
    -0.07
    ದಿ
    -0.07
     उठ
    -0.07
    POSITIVE LOGITS
     secund
    0.10
     luxurious
    0.09
     مستقیم
    0.08
     vro
    0.08
     sov
    0.08
     purpos
    0.08
     hii
    0.08
     dam
    0.08
     nauw
    0.08
     подробно
    0.08
    Activations Density 0.007%

    No Known Activations