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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 76505
    Prev
    Next
    INDEX
    Explanations

    security

    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
     정의
    -0.09
     얻
    -0.08
     Mittag
    -0.08
    ि�
    -0.07
    (blog
    -0.07
     BCN
    -0.07
     CAGR
    -0.07
     careg
    -0.07
     embroidered
    -0.07
     Sare
    -0.07
    POSITIVE LOGITS
     booths
    0.09
     screening
    0.09
     gevolgd
    0.08
     مخصوص
    0.08
    roat
    0.08
     lavagem
    0.08
     OPS
    0.08
    een
    0.08
    Checks
    0.08
     Screening
    0.08
    Activations Density 0.005%

    No Known Activations