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. 52894
    Prev
    Next
    INDEX
    Explanations

    hold

    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
    other
    -0.09
     обеспечения
    -0.09
     Manga
    -0.08
     virgin
    -0.08
     zer
    -0.07
     caj
    -0.07
    HW
    -0.07
     mellitus
    -0.07
     Tir
    -0.07
    hair
    -0.07
    POSITIVE LOGITS
     RBC
    0.09
     grud
    0.08
     neut
    0.08
    ERC
    0.07
     Been
    0.07
     Acr
    0.07
     prec
    0.07
    起来
    0.07
    屋
    0.07
     lidi
    0.07
    Activations Density 0.044%

    No Known Activations