© 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. 19-RESID-POST-AA
    11. 103047
    Prev
    Next
    INDEX
    Explanations

    first

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ήδη
    -0.08
     已
    -0.08
     and
    -0.08
     existing
    -0.07
     define
    -0.07
     ఇప్పటికే
    -0.07
     bereits
    -0.07
     或
    -0.07
     और
    -0.07
     पिछले
    -0.07
    POSITIVE LOGITS
     glance
    0.22
     кажется
    0.14
     glace
    0.13
     blush
    0.13
     glanced
    0.13
     parecia
    0.13
     seeming
    0.12
     pensé
    0.12
     взгляд
    0.11
    看来
    0.11
    Activations Density 0.012%

    No Known Activations