© 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. 79035
    Prev
    Next
    INDEX
    Explanations

    n

    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
     genocide
    -0.07
     ‍
    -0.07
     komple
    -0.07
     blindness
    -0.07
     violence
    -0.07
     footer
    -0.07
     chances
    -0.07
     repr
    -0.07
     envoy
    -0.07
     intelligence
    -0.07
    POSITIVE LOGITS
     sharpen
    0.09
     overgang
    0.08
     nua
    0.08
     Sharp
    0.08
     inex
    0.08
     solt
    0.08
     turma
    0.08
    jska
    0.08
     acestea
    0.08
     ésta
    0.08
    Activations Density 0.016%

    No Known Activations