© 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. 8087
    Prev
    Next
    INDEX
    Explanations

    countries

    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
     remote
    -0.09
     united
    -0.08
    遠
    -0.08
     ταξ
    -0.07
     get
    -0.07
    .remote
    -0.07
     off
    -0.07
     next
    -0.07
     temperaturen
    -0.07
     Remote
    -0.07
    POSITIVE LOGITS
    zcz
    0.11
     же
    0.10
    -created
    0.08
    UIAlert
    0.08
     maupun
    0.08
    anyị
    0.08
     Encourage
    0.08
     đôi
    0.08
    肤
    0.08
     indig
    0.08
    Activations Density 0.039%

    No Known Activations