© 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. 30946
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
     allocation
    -0.09
     earnings
    -0.08
     savings
    -0.08
    Allocate
    -0.08
    ร
    -0.08
     low
    -0.07
     peaks
    -0.07
    .jsdelivr
    -0.07
     digits
    -0.07
     allocations
    -0.07
    POSITIVE LOGITS
     geometr
    0.11
    pendicular
    0.10
     qry
    0.10
    .Geometry
    0.10
     benda
    0.10
     Geometry
    0.09
     leash
    0.09
     Quaternion
    0.09
     Relationship
    0.09
     Cone
    0.09
    Activations Density 0.031%

    No Known Activations