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. 15-RESID-POST-AA
    6. 18999
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jn
    -0.08
    visibility
    -0.07
     episode
    -0.07
    presence
    -0.07
    )}>
    -0.07
     jelly
    -0.07
    우
    -0.07
    Gill
    -0.07
    	size
    -0.07
     presence
    -0.07
    POSITIVE LOGITS
    其它
    0.13
     その他
    0.12
    .other
    0.12
     अन्य
    0.11
     другие
    0.11
     OTHER
    0.11
    其他
    0.11
     სხვა
    0.11
     други
    0.11
     دیگر
    0.11
    Activations Density 0.000%

    No Known Activations