© 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. 30905
    Prev
    Next
    INDEX
    Explanations

    car

    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
     assol
    -0.09
     ingress
    -0.08
     lập
    -0.08
     giant
    -0.07
     meg
    -0.07
     scarf
    -0.07
     Kas
    -0.07
     notion
    -0.07
     gross
    -0.07
     spectacular
    -0.07
    POSITIVE LOGITS
    remain
    0.09
    completed
    0.08
    Completed
    0.08
    collapsed
    0.08
    mates
    0.08
    corp
    0.08
    _completed
    0.08
    manual
    0.08
    translate
    0.08
    Collected
    0.08
    Activations Density 0.014%

    No Known Activations