© 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. 24616
    Prev
    Next
    INDEX
    Explanations

    because

    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
    Horn
    -0.07
    horn
    -0.07
    wayne
    -0.07
     logr
    -0.07
    一下
    -0.07
    ıy
    -0.07
    ieta
    -0.07
    Cartesian
    -0.07
     نیز
    -0.07
    roots
    -0.07
    POSITIVE LOGITS
     invés
    0.09
     believes
    0.09
     nobody
    0.09
     convinced
    0.09
     cias
    0.08
     clinical
    0.08
     utterly
    0.08
     believe
    0.08
    觉得
    0.08
     THAT
    0.08
    Activations Density 0.050%

    No Known Activations