© 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. 19-RESID-POST-AA
    11. 103042
    Prev
    Next
    INDEX
    Explanations

    cognitive skills

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ensured
    -0.10
     memastikan
    -0.08
    uwan
    -0.08
     freundlich
    -0.08
     меропр
    -0.08
    _ALLOW
    -0.08
     undesirable
    -0.08
     protecting
    -0.08
     unhealthy
    -0.08
    windows
    -0.08
    POSITIVE LOGITS
     skills
    0.18
     habilidades
    0.17
     навы
    0.16
     vaardigheden
    0.16
     compétences
    0.16
     comprehension
    0.15
     reasoning
    0.15
     compréhension
    0.15
     कौ
    0.15
    技能
    0.14
    Activations Density 0.012%

    No Known Activations