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. 15-RESID-POST-AA
    6. 18945
    Prev
    Next
    INDEX
    Explanations

    Sporting competition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vannak
    -0.08
    альными
    -0.08
     dishonest
    -0.08
     समाध
    -0.08
     مصادر
    -0.08
     satisfait
    -0.08
     enlist
    -0.08
     constat
    -0.07
    орон
    -0.07
    enç
    -0.07
    POSITIVE LOGITS
     matchup
    0.18
     rivalry
    0.16
     showdown
    0.16
     مباراة
    0.14
    双方
    0.13
     Between
    0.13
     pagitan
    0.13
     между
    0.13
     між
    0.13
    Between
    0.13
    Activations Density 0.086%

    No Known Activations