© 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. 19-RESID-POST-AA
    11. 102741
    Prev
    Next
    INDEX
    Explanations

    say "click"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .shiro
    -0.09
     poging
    -0.08
     begin
    -0.08
     quieren
    -0.08
     intending
    -0.08
     təhlük
    -0.08
     commencent
    -0.08
     înce
    -0.08
     spôsob
    -0.08
     sauvage
    -0.07
    POSITIVE LOGITS
    点击
    0.15
     clicar
    0.14
     클릭
    0.14
     klikken
    0.13
     klicken
    0.13
     क्लिक
    0.13
    クリック
    0.13
     点击
    0.13
    	click
    0.12
    .clicked
    0.12
    Activations Density 0.009%

    No Known Activations