© 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. 26423
    Prev
    Next
    INDEX
    Explanations

    Technical specifications in multiple languages

    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
     melodies
    -0.07
    \'
    -0.07
     Marshal
    -0.07
     chase
    -0.07
     overcome
    -0.07
    asure
    -0.07
    趣
    -0.07
    gets
    -0.07
     અસ
    -0.07
     designs
    -0.07
    POSITIVE LOGITS
     ได้แก่
    0.11
     principaux
    0.10
     commonly
    0.10
     principali
    0.10
     principales
    0.09
     suivants
    0.09
     wọnyi
    0.09
     incontourn
    0.09
     principais
    0.09
     pilares
    0.09
    Activations Density 0.103%

    No Known Activations