© 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. 78982
    Prev
    Next
    INDEX
    Explanations

    Exactly an amount

    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
     talaga
    -0.08
     odam
    -0.08
     associ
    -0.08
    Zap
    -0.07
    幻想
    -0.07
    리
    -0.07
     perder
    -0.07
     ligi
    -0.07
    ି
    -0.07
    XX
    -0.07
    POSITIVE LOGITS
    790
    0.08
    690
    0.08
    THER
    0.08
     частности
    0.08
     RANGE
    0.08
    ths
    0.08
     konkrete
    0.07
    höhe
    0.07
     aspire
    0.07
    .WEST
    0.07
    Activations Density 0.075%

    No Known Activations