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. 102940
    Prev
    Next
    INDEX
    Explanations

    course materials

    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
    nonce
    -0.07
    $response
    -0.07
     إطلاق
    -0.07
    দ
    -0.07
     bettors
    -0.07
    Localized
    -0.07
     partnered
    -0.07
    Emoji
    -0.07
    চ
    -0.07
     estan
    -0.07
    POSITIVE LOGITS
     semester
    0.16
     Semester
    0.14
     преподав
    0.14
     syllabus
    0.14
     Lecture
    0.14
    yllabus
    0.13
    Semester
    0.13
     دانشگاه
    0.13
     lectures
    0.13
     교수
    0.13
    Activations Density 0.055%

    No Known Activations