© 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. 29639
    Prev
    Next
    INDEX
    Explanations

    :

    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
    atsby
    -0.07
     ajudá
    -0.07
    舍
    -0.07
     Gull
    -0.07
    icular
    -0.07
    儿
    -0.07
    Libraries
    -0.07
     �
    -0.07
    普
    -0.07
    的话
    -0.07
    POSITIVE LOGITS
     HIM
    0.09
     ची
    0.09
     muted
    0.08
     CHE
    0.08
    уса
    0.08
    ikus
    0.08
     iche
    0.08
     lett
    0.08
     кара
    0.08
     fluent
    0.08
    Activations Density 0.006%

    No Known Activations