© 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. 47243
    Prev
    Next
    INDEX
    Explanations

    Exercise equipment

    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
     doctrine
    -0.08
     worldview
    -0.08
    	send
    -0.08
     assassination
    -0.08
     الأمن
    -0.08
    漏洞
    -0.08
     kader
    -0.08
     mistr
    -0.08
    afir
    -0.07
     שנים
    -0.07
    POSITIVE LOGITS
     treadmill
    0.11
     vélo
    0.10
     bicycles
    0.10
     bicicletas
    0.10
     jambes
    0.10
     wheelchair
    0.09
    -wheel
    0.09
     RPM
    0.09
     pedals
    0.09
     pedal
    0.09
    Activations Density 0.011%

    No Known Activations