Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52891
    Prev
    Next
    INDEX
    Explanations

    tack

    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
     sak
    -0.09
     heartfelt
    -0.08
    تف
    -0.08
    succ
    -0.08
     vraag
    -0.08
    mond
    -0.07
     Appar
    -0.07
    abox
    -0.07
     ilo
    -0.07
    agogue
    -0.07
    POSITIVE LOGITS
     tack
    0.10
    Duplicates
    0.08
     σου
    0.07
    مۇ
    0.07
    df
    0.07
     عالية
    0.07
     Canton
    0.07
     docket
    0.07
     ל
    0.07
     blem
    0.07
    Activations Density 0.001%

    No Known Activations