© 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. 47258
    Prev
    Next
    INDEX
    Explanations

    Work/business processes

    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
     الأسد
    -0.09
     angry
    -0.09
     ছেলে
    -0.09
     furious
    -0.09
     Angry
    -0.09
    ార్
    -0.09
     Rifle
    -0.09
     వచ్చింది
    -0.09
     Artist
    -0.09
     Conditioner
    -0.08
    POSITIVE LOGITS
     stakeholders
    0.09
    制定
    0.08
    完善
    0.08
     �
    0.08
     interventions
    0.08
     opportunities
    0.08
     multidisciplinary
    0.08
    �
    0.08
     során
    0.08
     בתחום
    0.08
    Activations Density 0.086%

    No Known Activations