© 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. 129539
    Prev
    Next
    INDEX
    Explanations

    sun

    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
     Download
    -0.08
     विवरण
    -0.07
     Tril
    -0.07
     Ress
    -0.07
     등장
    -0.07
     goeie
    -0.07
    (Result
    -0.07
    รายการ
    -0.07
    分钱
    -0.07
    -instance
    -0.07
    POSITIVE LOGITS
     exposure
    0.10
     exposures
    0.10
     وتأ
    0.09
    攝
    0.09
     externo
    0.09
     воздейств
    0.08
    摄
    0.08
     externas
    0.08
     protecting
    0.08
     assaults
    0.08
    Activations Density 0.007%

    No Known Activations