© 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. 24763
    Prev
    Next
    INDEX
    Explanations

    Before/prior events

    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
     mark
    -0.08
    นี่
    -0.07
    力度
    -0.07
    Kom
    -0.07
     intrig
    -0.07
    -height
    -0.07
    jeu
    -0.07
     implicitly
    -0.07
    商品の
    -0.07
     jedna
    -0.07
    POSITIVE LOGITS
    正式
    0.09
     widespread
    0.08
     Quote
    0.08
     siquiera
    0.08
    Quote
    0.08
     börjar
    0.08
     mitään
    0.07
     �
    0.07
     totalement
    0.07
     ďal
    0.07
    Activations Density 0.168%

    No Known Activations