© 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. 23-RESID-POST-AA
    11. 48521
    Prev
    Next
    INDEX
    Explanations

    supplements

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मिलता
    -0.08
    ab
    -0.07
     Arr
    -0.07
     Fashion
    -0.07
     Kinder
    -0.07
     Ab
    -0.07
     Cabin
    -0.07
     Cav
    -0.07
     cv
    -0.07
     olup
    -0.07
    POSITIVE LOGITS
    [assembly
    0.08
    [target
    0.08
    0.08
    øg
    0.08
    ตอน
    0.08
     început
    0.08
    メント
    0.08
    삭제
    0.08
     거리
    0.08
     선언
    0.08
    Activations Density 0.000%

    No Known Activations