© 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. 24726
    Prev
    Next
    INDEX
    Explanations

    numbered items

    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
     fizik
    -0.09
     Beckham
    -0.08
    oma
    -0.08
     Democrat
    -0.08
     masa
    -0.08
    wati
    -0.08
    jetër
    -0.08
    ismus
    -0.08
     Attorney
    -0.08
     Blau
    -0.08
    POSITIVE LOGITS
     ranging
    0.10
    abcdefghijklmnopqrstuvwxyz
    0.08
     ranges
    0.08
     numbered
    0.08
     amongst
    0.08
     numbering
    0.07
     pilgrims
    0.07
    lek
    0.07
    ಕರಣ
    0.07
     ranged
    0.07
    Activations Density 0.006%

    No Known Activations