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. 3-RESID-POST-AA
    6. 12428
    Prev
    Next
    INDEX
    Explanations

    diagonal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xx
    -0.08
    що
    -0.08
     شنا
    -0.07
     Jacobs
    -0.07
    golly
    -0.07
    smål
    -0.07
    ગી
    -0.07
     Anniversary
    -0.07
     NSString
    -0.07
     chrysanthemums
    -0.07
    POSITIVE LOGITS
     constr
    0.09
     Bis
    0.08
    _Block
    0.08
    wege
    0.07
     Baj
    0.07
    �
    0.07
     пись
    0.07
    Bis
    0.07
    辅
    0.07
    bial
    0.07
    Activations Density 0.014%

    No Known Activations