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. 44830
    Prev
    Next
    INDEX
    Explanations

    mention

    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
    �
    -0.09
     নাট
    -0.08
    ങ്ങിയ
    -0.08
    傷
    -0.08
     inédit
    -0.08
     imaginable
    -0.08
     పుర
    -0.08
    .anim
    -0.08
    azionale
    -0.08
    constitutional
    -0.07
    POSITIVE LOGITS
     caution
    0.09
     pitfalls
    0.09
     Wichtig
    0.08
     beginners
    0.08
     handling
    0.08
     כיצד
    0.08
     注意
    0.08
     วิธี
    0.08
     ശ്രദ്ധ
    0.08
    注意
    0.08
    Activations Density 0.047%

    No Known Activations