© 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. 91393
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     paragraph
    -0.09
    _phrase
    -0.08
     thesis
    -0.07
    sentence
    -0.07
     Thesis
    -0.07
    paragraph
    -0.07
    pert
    -0.07
     fixes
    -0.07
     divides
    -0.07
     Paragraph
    -0.07
    POSITIVE LOGITS
     negativ
    0.10
     negativity
    0.10
     positif
    0.10
     negatif
    0.10
    하거나
    0.09
     negativa
    0.09
    atiiv
    0.09
     nebo
    0.09
     positivity
    0.09
     отриц
    0.08
    Activations Density 0.207%

    No Known Activations