© 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. 570
    Prev
    Next
    INDEX
    Explanations

    comment

    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
    Simulation
    -0.08
    Blood
    -0.08
    blood
    -0.08
     sauver
    -0.08
     <↵
    -0.07
    simulation
    -0.07
    焼
    -0.07
     blood
    -0.07
     Simulation
    -0.07
    Unique
    -0.07
    POSITIVE LOGITS
    ాతం
    0.10
    透露
    0.09
     Mourinho
    0.08
     gossip
    0.08
     المتعلقة
    0.08
    内幕
    0.08
     insider
    0.08
     Amount
    0.08
     disclose
    0.07
    -strength
    0.07
    Activations Density 0.026%

    No Known Activations