© 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. 45256
    Prev
    Next
    INDEX
    Explanations

    articles (a, the)

    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
     выяв
    -0.08
     pointer
    -0.08
     pien
    -0.08
     Carmel
    -0.08
    ',{
    -0.08
     pointe
    -0.08
     Breeze
    -0.07
    [o
    -0.07
    castle
    -0.07
     Freib
    -0.07
    POSITIVE LOGITS
     समारोह
    0.09
     অনুষ্ঠ
    0.09
     speeches
    0.09
     announcing
    0.08
    Announcement
    0.08
     alma
    0.08
     proceedings
    0.08
     অনুষ্ঠান
    0.08
     Forbes
    0.08
     टीवी
    0.08
    Activations Density 0.048%

    No Known Activations