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. 8926
    Prev
    Next
    INDEX
    Explanations

    qualifications

    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
     Med
    -0.08
    TEC
    -0.08
    靠
    -0.07
    Processing
    -0.07
    ipation
    -0.07
    310
    -0.07
    ట్టు
    -0.07
     teh
    -0.07
     med
    -0.07
    Quadr
    -0.07
    POSITIVE LOGITS
     repreh
    0.09
     marami
    0.08
     sophomore
    0.08
     sympathetic
    0.08
     charming
    0.08
    ですが
    0.08
    ιο
    0.08
     знакомства
    0.08
    іць
    0.08
     खोज
    0.07
    Activations Density 0.006%

    No Known Activations