© 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. 45283
    Prev
    Next
    INDEX
    Explanations

    repeating decimals

    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
     Vitt
    -0.08
     renamed
    -0.08
     Team
    -0.07
     Jays
    -0.07
     Bah
    -0.07
    rename
    -0.07
     antagon
    -0.07
    nergies
    -0.07
     events
    -0.07
    .cas
    -0.07
    POSITIVE LOGITS
    Finite
    0.11
     алгорит
    0.10
     получение
    0.10
     അവസാന
    0.10
    rstrip
    0.09
    Digits
    0.09
     конеч
    0.09
    FINITE
    0.09
     finite
    0.09
     termijn
    0.09
    Activations Density 0.011%

    No Known Activations