© 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. 94999
    Prev
    Next
    INDEX
    Explanations

    's

    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
     kommunen
    -0.08
     mm
    -0.08
     vasos
    -0.07
    -0.07
     fech
    -0.07
    aski
    -0.07
     Memphis
    -0.07
    .mm
    -0.07
     tó
    -0.07
     buscando
    -0.07
    POSITIVE LOGITS
    人员
    0.14
     beings
    0.14
    人物
    0.13
    ’abantu
    0.12
     mmadụ
    0.12
     munhu
    0.12
     tagata
    0.12
     사람
    0.12
     eniyan
    0.12
     الأشخاص
    0.12
    Activations Density 0.371%
    No Known Activations