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. 65198
    Prev
    Next
    INDEX
    Explanations

    free will

    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
    (:
    -0.08
    数字
    -0.07
    ierra
    -0.07
     kissing
    -0.07
    Digital
    -0.07
    Object
    -0.07
    েই
    -0.07
     kite
    -0.07
     streamer
    -0.07
    lings
    -0.07
    POSITIVE LOGITS
     إر
    0.11
     નિર્ણય
    0.11
     সিদ্ধান্ত
    0.10
     నిర్ణ
    0.10
     الإر
    0.10
     স্বাধীন
    0.09
     ಪ್ರಶ್ನ
    0.09
     തീരുമാന
    0.09
     تصمیم
    0.09
     выбора
    0.09
    Activations Density 0.006%

    No Known Activations