Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88110
    Prev
    Next
    INDEX
    Explanations

    headphone jack

    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
     té
    -0.08
    ova
    -0.08
     jakie
    -0.08
    orbit
    -0.08
    един
    -0.07
    oreen
    -0.07
    ূহ
    -0.07
     тей
    -0.07
    drive
    -0.07
    وري
    -0.07
    POSITIVE LOGITS
     ποσ
    0.08
    SZ
    0.07
     mikt
    0.07
     mistake
    0.07
     kaso
    0.07
     लोगो
    0.07
    BLACK
    0.07
     schr
    0.07
     చిత్రం
    0.07
    logo
    0.07
    Activations Density 0.001%

    No Known Activations