© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99309
    Prev
    Next
    INDEX
    Explanations

    lower

    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
     newcomer
    -0.08
     domic
    -0.07
    Typ
    -0.07
     поддерж
    -0.07
     Nepal
    -0.07
    协
    -0.07
    ?n
    -0.07
     sel
    -0.07
     governed
    -0.07
     преб
    -0.07
    POSITIVE LOGITS
    -bottom
    0.09
     marque
    0.08
     भारी
    0.08
    頃
    0.08
     हिस्स
    0.08
     lance
    0.08
     ऊ
    0.08
    -century
    0.08
     morceaux
    0.07
    頁
    0.07
    Activations Density 0.003%

    No Known Activations