© 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. 627
    Prev
    Next
    INDEX
    Explanations

    补

    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
     Russell
    -0.08
    时候
    -0.08
    crow
    -0.08
     mellitus
    -0.07
     Мир
    -0.07
     dormant
    -0.07
     Raim
    -0.07
     René
    -0.07
     crimson
    -0.07
     Vish
    -0.07
    POSITIVE LOGITS
    措施
    0.09
    61
    0.08
    itionally
    0.08
    maßnahmen
    0.07
     जब
    0.07
    娛樂
    0.07
    �
    0.07
    .Scope
    0.07
     aux
    0.07
     मज
    0.07
    Activations Density 0.008%

    No Known Activations