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. 44808
    Prev
    Next
    INDEX
    Explanations

    on

    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
     exercise
    -0.08
     lorem
    -0.08
     nationally
    -0.08
    េះ
    -0.08
     defined
    -0.08
     μεταξύ
    -0.08
     возникновения
    -0.08
     paved
    -0.08
     overly
    -0.08
    jsonp
    -0.07
    POSITIVE LOGITS
     મૂક
    0.09
     dulce
    0.08
     મુક
    0.08
     Inclusion
    0.08
     lev
    0.08
     размещ
    0.08
    -counter
    0.07
     incandescent
    0.07
     орнал
    0.07
    AIS
    0.07
    Activations Density 0.005%

    No Known Activations