© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78479
    Prev
    Next
    INDEX
    Explanations

    Medicinal and health benefits

    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
    Fors
    -0.08
    irango
    -0.08
    વિ
    -0.08
     elite
    -0.08
     uranium
    -0.08
     platinum
    -0.08
    etto
    -0.07
    -bank
    -0.07
     swimmers
    -0.07
    ření
    -0.07
    POSITIVE LOGITS
    اده
    0.08
     ailments
    0.08
    .concat
    0.08
     lösen
    0.08
     hre
    0.08
     వే�
    0.08
    dl
    0.07
     dl
    0.07
     مذا
    0.07
     break
    0.07
    Activations Density 0.013%

    No Known Activations