© 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. 47189
    Prev
    Next
    INDEX
    Explanations

    Antwort

    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
    Unter
    -0.08
     Under
    -0.08
     Step
    -0.07
     sotto
    -0.07
     troublesome
    -0.07
     rapproche
    -0.07
    Under
    -0.07
    ),'
    -0.07
     tiring
    -0.07
    566
    -0.07
    POSITIVE LOGITS
     bitte
    0.08
     пожалуйста
    0.08
     देंगे
    0.08
     będ
    0.08
     garantia
    0.08
     nanti
    0.08
     mel
    0.08
    _SQL
    0.07
     emi
    0.07
     Será
    0.07
    Activations Density 0.010%

    No Known Activations