© 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. 23-RESID-POST-AA
    11. 96818
    Prev
    Next
    INDEX
    Explanations

    ater

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     野
    -0.09
     �
    -0.08
     国
    -0.08
     Fleming
    -0.08
     europe
    -0.08
     �
    -0.08
    keer
    -0.08
     信
    -0.08
     paire
    -0.07
     Jonathan
    -0.07
    POSITIVE LOGITS
    ia
    0.08
     উদ্ব
    0.08
     સામ
    0.08
    افي
    0.07
    ું
    0.07
     পানি
    0.07
    ২৬
    0.07
    াথমিক
    0.07
     unbiased
    0.07
     মাস
    0.07
    Activations Density 0.000%

    No Known Activations