© 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. 123
    Prev
    Next
    INDEX
    Explanations

    difference

    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
     개선
    -0.08
     intro
    -0.08
     �
    -0.08
     avenir
    -0.07
     Gy
    -0.07
     소개
    -0.07
     indications
    -0.07
     improvements
    -0.07
    ikum
    -0.07
    통
    -0.07
    POSITIVE LOGITS
     granda
    0.08
    Стоимость
    0.08
    vation
    0.08
     difference
    0.08
     bzw
    0.08
    即可
    0.08
     lihtsalt
    0.08
     nascimento
    0.08
     Veranst
    0.08
     katta
    0.08
    Activations Density 0.011%

    No Known Activations