© 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. 129464
    Prev
    Next
    INDEX
    Explanations

    arithmetic progressions

    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
     multinational
    -0.08
     jackets
    -0.08
    估
    -0.07
     최대
    -0.07
     sensor
    -0.07
    ୀ
    -0.07
     modem
    -0.07
     resumes
    -0.07
    Biography
    -0.07
     unclear
    -0.07
    POSITIVE LOGITS
     encouragement
    0.08
     sentado
    0.08
     urge
    0.08
    'esprit
    0.08
     apartado
    0.08
    ffaa
    0.08
    .Iter
    0.08
     tids
    0.07
    baka
    0.07
     tsak
    0.07
    Activations Density 0.006%

    No Known Activations