© 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. 649
    Prev
    Next
    INDEX
    Explanations

    called

    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
    ldquo
    -0.08
    FFT
    -0.08
    -thumbnail
    -0.08
     outstanding
    -0.08
    afone
    -0.07
     Linked
    -0.07
    ıklı
    -0.07
     commonly
    -0.07
     insightful
    -0.07
    quez
    -0.07
    POSITIVE LOGITS
     boarding
    0.08
     иде
    0.08
     steun
    0.08
     wenden
    0.08
     HO
    0.08
     ideals
    0.07
    owner
    0.07
     ideales
    0.07
     المس
    0.07
     المع
    0.07
    Activations Density 0.000%

    No Known Activations