© 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. 8207
    Prev
    Next
    INDEX
    Explanations

    keyboards and buttons

    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
     spend
    -0.08
     diagnosed
    -0.07
    Nich
    -0.07
     competitors
    -0.07
     inflation
    -0.07
    eref
    -0.07
     spends
    -0.07
     spending
    -0.07
     seuil
    -0.07
     growth
    -0.07
    POSITIVE LOGITS
     клав
    0.11
     кнопку
    0.11
     кноп
    0.11
     botão
    0.10
    	JButton
    0.09
     botón
    0.09
     Shift
    0.09
    按钮
    0.09
     버튼
    0.09
     ჩვენ
    0.09
    Activations Density 0.003%

    No Known Activations