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. 11662
    Prev
    Next
    INDEX
    Explanations

    le

    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
     dr
    -0.08
     pierced
    -0.08
    洞
    -0.08
     piercing
    -0.08
    凰
    -0.08
     pier
    -0.08
     claws
    -0.07
     vort
    -0.07
     petr
    -0.07
    穿
    -0.07
    POSITIVE LOGITS
    (android
    0.07
    Classpath
    0.07
    Runner
    0.07
     الدراسي
    0.07
     ста
    0.07
    buch
    0.07
     fete
    0.07
    classpath
    0.07
    优化
    0.07
    (script
    0.07
    Activations Density 0.001%

    No Known Activations