© 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. 129427
    Prev
    Next
    INDEX
    Explanations

    pagination

    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
    i
    -0.08
    a
    -0.08
    .arrow
    -0.07
    ly
    -0.07
    огод
    -0.07
     Breath
    -0.07
    REATE
    -0.07
     thoughtfully
    -0.07
    .days
    -0.07
    .card
    -0.07
    POSITIVE LOGITS
    steen
    0.08
    λικ
    0.08
    لوم
    0.08
     bygger
    0.08
     stenen
    0.08
     lina
    0.08
     waarschijnlijk
    0.08
     altru
    0.08
     exploiting
    0.08
     informação
    0.08
    Activations Density 0.001%

    No Known Activations