© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 114055
    Prev
    Next
    INDEX
    Explanations

    Memoir prompts

    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
     चले
    -0.08
     Dangerous
    -0.08
     Егер
    -0.08
     सुविध
    -0.08
     nasty
    -0.08
     ДТП
    -0.08
     �
    -0.08
    izeit
    -0.08
    айтесь
    -0.08
     автобус
    -0.08
    POSITIVE LOGITS
     resilience
    0.10
     humility
    0.09
     patience
    0.09
     mindfulness
    0.08
     kindness
    0.08
     believing
    0.08
     puzzle
    0.08
     tapestry
    0.08
     compassion
    0.08
    deb
    0.07
    Activations Density 0.028%

    No Known Activations