© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 26518
    Prev
    Next
    INDEX
    Explanations

    communication

    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
     Offset
    -0.10
    _offset
    -0.08
    Offset
    -0.08
     offset
    -0.08
     skips
    -0.08
     notable
    -0.08
    	offset
    -0.08
     wandering
    -0.07
     '
    -0.07
     offsets
    -0.07
    POSITIVE LOGITS
    沟
    0.14
     überzeug
    0.13
     communicate
    0.12
     communicatie
    0.12
     convaincre
    0.11
     전달
    0.11
     communicating
    0.11
     conveying
    0.11
     persuade
    0.11
     communicated
    0.11
    Activations Density 0.030%

    No Known Activations