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. 26756
    Prev
    Next
    INDEX
    Explanations

    Code and math

    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
    یده
    -0.08
    (pe
    -0.08
    parcel
    -0.08
     Lan
    -0.08
    trat
    -0.08
    ೀಯ
    -0.08
    ез
    -0.08
    reinterpret
    -0.07
    anvas
    -0.07
    con
    -0.07
    POSITIVE LOGITS
     prevalence
    0.08
     जोड़
    0.07
    লী
    0.07
     prisión
    0.07
     Steven
    0.07
     hv
    0.07
     imprisoned
    0.07
     abandon
    0.07
     عم
    0.07
     Virginia
    0.07
    Activations Density 0.001%

    No Known Activations