© 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. 65049
    Prev
    Next
    INDEX
    Explanations

    environment

    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
     الدخول
    -0.08
     voire
    -0.07
     feat
    -0.07
     Glenn
    -0.07
    Criterion
    -0.07
     отдель
    -0.07
     ביק
    -0.06
     področ
    -0.06
     III
    -0.06
     aptly
    -0.06
    POSITIVE LOGITS
    因素
    0.11
     surroundings
    0.10
     സാഹചര്യ
    0.10
     factors
    0.10
     окружа
    0.09
     circunstancias
    0.09
     circumstances
    0.09
     factores
    0.09
     omstandigheden
    0.09
    .environment
    0.09
    Activations Density 0.017%

    No Known Activations