© 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. 44907
    Prev
    Next
    INDEX
    Explanations

    response

    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
     outsider
    -0.09
     downward
    -0.09
    geme
    -0.08
     revival
    -0.08
     offense
    -0.08
    -0.08
    -account
    -0.08
    кид
    -0.08
     curricula
    -0.08
     overlooks
    -0.08
    POSITIVE LOGITS
     trả
    0.11
    返
    0.09
     returned
    0.09
     Returned
    0.08
    returned
    0.08
    Received
    0.08
     Aç
    0.07
     Lydia
    0.07
    /API
    0.07
     Pho
    0.07
    Activations Density 0.006%
    No Known Activations