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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12706
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     precip
    -0.09
    ഴ
    -0.08
    antly
    -0.08
     ti
    -0.08
     jednom
    -0.07
    后的
    -0.07
    otso
    -0.07
     fragments
    -0.07
     fruct
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    ици
    0.08
     archiv
    0.07
     lect
    0.07
     Mitt
    0.07
     Ford
    0.07
     напомина
    0.07
     Lee
    0.07
    盘
    0.07
     Bayer
    0.07
     чем
    0.07
    Activations Density 0.001%

    No Known Activations