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. 58324
    Prev
    Next
    INDEX
    Explanations

    Excerpts from diverse documents

    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
     ذري
    -0.09
     notwend
    -0.09
     tadi
    -0.09
     nayo
    -0.09
     ေန
    -0.09
    ’existence
    -0.09
     pobj
    -0.08
     المذك
    -0.08
     nodige
    -0.08
     ဆို
    -0.08
    POSITIVE LOGITS
     and
    0.11
    :
    0.11
     (
    0.11
    ,
    0.10
    /
    0.10
    .
    0.10
    -
    0.10
     
    0.09
    (
    0.09
    1
    0.09
    Activations Density 1.389%

    No Known Activations