Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 75379
    Prev
    Next
    INDEX
    Explanations

    Edison

    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
     lapar
    -0.09
    ün
    -0.09
     орын
    -0.07
     Bale
    -0.07
    laşdır
    -0.07
    ğunu
    -0.07
    ın
    -0.07
    üs
    -0.07
     étage
    -0.07
     Tig
    -0.07
    POSITIVE LOGITS
     Palmer
    0.09
     patience
    0.08
    申
    0.08
     patents
    0.08
     RCA
    0.07
    ługi
    0.07
     productivity
    0.07
    ordi
    0.07
     paciencia
    0.07
    เลย
    0.07
    Activations Density 0.001%

    No Known Activations