© 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. 7992
    Prev
    Next
    INDEX
    Explanations

    searching and finding

    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
     Eu
    -0.09
     Nicola
    -0.08
     fixation
    -0.08
     mag
    -0.08
    \Base
    -0.07
     claim
    -0.07
    Eu
    -0.07
     normalization
    -0.07
     macht
    -0.07
    ekayo
    -0.07
    POSITIVE LOGITS
    Buckets
    0.11
     buckets
    0.09
    排序
    0.09
    Bucket
    0.08
     ranked
    0.08
    STREAM
    0.08
    袋
    0.08
     Abby
    0.08
    ไ
    0.08
    桶
    0.08
    Activations Density 0.004%

    No Known Activations