© 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. 746
    Prev
    Next
    INDEX
    Explanations

    Manufacturing process improvement

    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
     Meadow
    -0.12
     meadow
    -0.09
    amantha
    -0.09
     Ellie
    -0.08
     keel
    -0.08
    .degree
    -0.08
    ще
    -0.08
     Brew
    -0.08
    ygy
    -0.08
     kelle
    -0.08
    POSITIVE LOGITS
    现场
    0.08
    0.08
    Routine
    0.07
     abduct
    0.07
     locais
    0.07
     prophyl
    0.07
     instaur
    0.07
     techniques
    0.07
    oint
    0.07
     abd
    0.07
    Activations Density 0.003%
    No Known Activations