© 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. 78360
    Prev
    Next
    INDEX
    Explanations

    quick ratio

    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
    ��
    -0.08
    ��
    -0.07
    CIÓN
    -0.07
    でしょう
    -0.07
    صدر
    -0.07
    朋
    -0.07
     sle
    -0.07
     gete
    -0.07
    ién
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     общ
    0.08
     molho
    0.08
     характерист
    0.08
     caract
    0.08
    	Element
    0.08
     softwares
    0.08
    .Element
    0.07
     interna
    0.07
    Attachment
    0.07
    Firestore
    0.07
    Activations Density 0.000%

    No Known Activations