© 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. 31008
    Prev
    Next
    INDEX
    Explanations

    positive

    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
     burdens
    -0.08
     Vladimir
    -0.08
     graphi
    -0.08
    691
    -0.08
     graphique
    -0.08
     Steve
    -0.07
    -0.07
    $args
    -0.07
    Buk
    -0.07
     Remark
    -0.07
    POSITIVE LOGITS
     mesas
    0.08
     wsz
    0.08
    0.08
     клав
    0.08
     वाली
    0.08
     cym
    0.07
     tərəfind
    0.07
     ions
    0.07
     polarity
    0.07
     tərə
    0.07
    Activations Density 0.005%
    No Known Activations