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. 55790
    Prev
    Next
    INDEX
    Explanations

    Image

    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
     BIOS
    -0.08
     breathed
    -0.08
     benz
    -0.08
    circ
    -0.08
     przem
    -0.08
     billed
    -0.08
     acompanh
    -0.08
     két
    -0.08
     circum
    -0.08
     HPV
    -0.08
    POSITIVE LOGITS
     homogen
    0.08
     voorbereiding
    0.08
     voorbere
    0.08
     deren
    0.07
     разработ
    0.07
    ож
    0.07
     Maiden
    0.07
    vale
    0.07
     ontwikk
    0.07
     feit
    0.07
    Activations Density 0.001%

    No Known Activations