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. 59150
    Prev
    Next
    INDEX
    Explanations

    Mathematics

    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
     still
    -0.08
    首
    -0.07
    �
    -0.07
     jud
    -0.07
    ropic
    -0.07
     likes
    -0.07
    ından
    -0.07
    ".↵↵
    -0.07
     ви
    -0.07
    並
    -0.06
    POSITIVE LOGITS
     comprado
    0.09
    شراء
    0.09
    امن
    0.08
    geza
    0.08
     acheté
    0.08
     بنانے
    0.08
    ickt
    0.08
    						
    0.08
    多少钱
    0.08
     Girona
    0.07
    Activations Density 0.318%

    No Known Activations