© 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. 3-RESID-POST-AA
    11. 2773
    Prev
    Next
    INDEX
    Explanations

    low

    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
    523
    -0.08
     pee
    -0.08
     Stre
    -0.08
    -ant
    -0.08
    quest
    -0.08
     elementary
    -0.07
    526
    -0.07
     exporting
    -0.07
    608
    -0.07
     Ehr
    -0.07
    POSITIVE LOGITS
     surprises
    0.10
     reliance
    0.09
    掉
    0.09
    ാതെ
    0.08
    ترل
    0.08
     ADM
    0.08
    -invasive
    0.08
    廉
    0.08
    须
    0.08
    .strip
    0.08
    Activations Density 0.147%

    No Known Activations