© 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. 94930
    Prev
    Next
    INDEX
    Explanations

    symmetric sums

    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
    Blocked
    -0.09
     arterial
    -0.09
     vaso
    -0.08
     minorities
    -0.08
    Cry
    -0.08
     Blocking
    -0.08
    Blocking
    -0.08
     comple
    -0.08
    inen
    -0.08
     asleep
    -0.08
    POSITIVE LOGITS
    .euler
    0.09
     properties
    0.09
     Euler
    0.09
    kundige
    0.08
     facts
    0.08
     coll
    0.08
     Facts
    0.08
     Moments
    0.08
    properties
    0.08
     quint
    0.08
    Activations Density 0.053%

    No Known Activations