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. 102812
    Prev
    Next
    INDEX
    Explanations

    (x,y) equations

    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
    र्ज
    -0.07
     chick
    -0.07
     Er
    -0.07
    Er
    -0.07
     ratt
    -0.07
     lector
    -0.07
     �
    -0.07
    oggi
    -0.07
    /no
    -0.07
    -ROM
    -0.06
    POSITIVE LOGITS
     ஆகிய
    0.08
     HV
    0.08
     Fundamentals
    0.08
     Wij
    0.07
     úd
    0.07
     Colours
    0.07
     Dining
    0.07
    っぱい
    0.07
     Sodium
    0.07
     rebuilding
    0.07
    Activations Density 0.024%

    No Known Activations