© 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. 69091
    Prev
    Next
    INDEX
    Explanations

    istic

    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
     curvature
    -0.08
    relationship
    -0.08
    relationships
    -0.08
    yai
    -0.08
     Relationship
    -0.08
     порядок
    -0.08
     leon
    -0.07
     relationship
    -0.07
    Relationship
    -0.07
     interp
    -0.07
    POSITIVE LOGITS
     Marx
    0.08
    Coming
    0.08
     Handlung
    0.07
     verbs
    0.07
    (numero
    0.07
     prix
    0.07
     Ә
    0.07
    Autowired
    0.07
    verfahren
    0.07
    Prix
    0.07
    Activations Density 0.003%

    No Known Activations