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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58698
    Prev
    Next
    INDEX
    Explanations

    But/Is

    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
     बिग
    -0.10
     به
    -0.09
     years
    -0.08
     elucid
    -0.08
     cok
    -0.08
    (year
    -0.07
     nhận
    -0.07
     preços
    -0.07
    μορ
    -0.07
     Κ
    -0.07
    POSITIVE LOGITS
     некоторых
    0.10
    .@
    0.10
    は禁止
    0.10
    Safe
    0.09
     unavoidable
    0.09
     complies
    0.09
     Safety
    0.08
     Safe
    0.08
     безопас
    0.08
    safe
    0.08
    Activations Density 0.014%

    No Known Activations