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. 468
    Prev
    Next
    INDEX
    Explanations

    of

    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
     chiar
    -0.08
    నే
    -0.08
     Vereins
    -0.08
     ਹੀ
    -0.07
    ~~~
    -0.07
     desal
    -0.07
    constitutional
    -0.07
    werte
    -0.07
    yards
    -0.07
    (),↵
    -0.07
    POSITIVE LOGITS
    iplina
    0.08
     Osc
    0.08
     slav
    0.08
    数据显示
    0.08
     Melody
    0.07
     Cig
    0.07
     oscill
    0.07
     Talking
    0.07
    去哪
    0.07
     ov
    0.07
    Activations Density 0.089%

    No Known Activations