© 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. 78992
    Prev
    Next
    INDEX
    Explanations

    percentage changes

    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
     убед
    -0.09
     retire
    -0.08
    Range
    -0.08
     Range
    -0.08
     range
    -0.07
     Ip
    -0.07
     retiring
    -0.07
     можно
    -0.07
     Taste
    -0.07
     low
    -0.07
    POSITIVE LOGITS
     ভিত্ত
    0.09
     Grundlage
    0.09
     기준
    0.09
     आधार
    0.09
     આધાર
    0.09
    (base
    0.08
    括
    0.08
    本金
    0.08
    ollar
    0.08
    ummaa
    0.08
    Activations Density 0.072%

    No Known Activations