© 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. 108641
    Prev
    Next
    INDEX
    Explanations

    awkward language

    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
    (regex
    -0.09
    397
    -0.08
    aae
    -0.08
     Lad
    -0.08
    (**
    -0.07
    ihi
    -0.07
    (图
    -0.07
     vigente
    -0.07
     regex
    -0.07
    xca
    -0.07
    POSITIVE LOGITS
     phr
    0.09
     clich
    0.09
     demasiado
    0.09
     terlalu
    0.09
     contradict
    0.09
     unnecessary
    0.09
     unclear
    0.08
     nons
    0.08
     слишком
    0.08
     너무
    0.08
    Activations Density 0.020%

    No Known Activations