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. 112564
    Prev
    Next
    INDEX
    Explanations

    floor and ceil

    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
    mais
    -0.08
     fibr
    -0.07
     filing
    -0.07
     pek
    -0.07
    머
    -0.07
    pe
    -0.07
    inye
    -0.07
    裂
    -0.07
     !==
    -0.07
    ம
    -0.07
    POSITIVE LOGITS
    ERROR
    0.09
     Hội
    0.09
     Бер
    0.08
    {↵↵
    0.08
     Kann
    0.08
     तँ
    0.08
     Finanzierung
    0.08
     ֆինանս
    0.08
    EVER
    0.08
     разоб
    0.07
    Activations Density 0.035%

    No Known Activations