© 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. 78784
    Prev
    Next
    INDEX
    Explanations

    with

    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
     Stevenson
    -0.08
    itiro
    -0.08
     ved
    -0.07
    -0.07
     Ern
    -0.07
     Ned
    -0.07
     Malmö
    -0.07
    一下
    -0.07
     Ded
    -0.07
    currency
    -0.07
    POSITIVE LOGITS
     ideeën
    0.08
     Freude
    0.08
     opdrachten
    0.07
     incr
    0.07
     qiym
    0.07
     કિં
    0.07
     certificates
    0.07
     haine
    0.07
     enthusiasm
    0.07
    Apr
    0.07
    Activations Density 0.021%

    No Known Activations