Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77555
    Prev
    Next
    INDEX
    Explanations

    educational games and concepts

    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
    αρ
    -0.08
     insiders
    -0.08
    热线
    -0.08
    feb
    -0.08
     aho
    -0.08
     Fic
    -0.07
    袭
    -0.07
     поступ
    -0.07
    beb
    -0.07
     mele
    -0.07
    POSITIVE LOGITS
     teamwork
    0.11
    ლ
    0.10
     perseverance
    0.10
    尊
    0.09
     reinforces
    0.09
     concepts
    0.09
    าธ
    0.09
     coordinación
    0.09
    技巧
    0.09
    技能
    0.09
    Activations Density 0.068%

    No Known Activations