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. 65808
    Prev
    Next
    INDEX
    Explanations

    body

    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
    _GRAY
    -0.08
     đọc
    -0.07
     verbal
    -0.07
    rá
    -0.07
    	pc
    -0.07
     NORTH
    -0.07
     rencontré
    -0.07
    Exc
    -0.07
    까
    -0.07
     emocionante
    -0.07
    POSITIVE LOGITS
     holistic
    0.12
     wellness
    0.10
     Wellness
    0.10
     Ayur
    0.09
     Ayurveda
    0.09
    hol
    0.08
     wellbeing
    0.08
     sana
    0.08
     хол
    0.08
     inteira
    0.08
    Activations Density 0.006%

    No Known Activations