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. 101643
    Prev
    Next
    INDEX
    Explanations

    Unparsed text/data

    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
    /path
    -0.10
     ರಸ್ತೆ
    -0.10
    /root
    -0.09
     ರಸ್ತ
    -0.09
    /f
    -0.08
    /artificial
    -0.08
     tissues
    -0.08
    /default
    -0.08
    _ALIGNMENT
    -0.08
    (rep
    -0.08
    POSITIVE LOGITS
    erializer
    0.09
     Bahasa
    0.07
    Though
    0.07
    ↵↵↵↵↵↵
    0.07
    。↵↵↵↵
    0.07
    860
    0.07
     multilingual
    0.07
    Milk
    0.07
    though
    0.07
     choć
    0.07
    Activations Density 0.244%

    No Known Activations