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. 78611
    Prev
    Next
    INDEX
    Explanations

    Math equations

    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
    wake
    -0.08
    અમ
    -0.08
     olmayan
    -0.08
     തൊഴില
    -0.08
     يحصل
    -0.07
     nyata
    -0.07
     niemals
    -0.07
     land
    -0.07
    ઢ
    -0.07
     west
    -0.07
    POSITIVE LOGITS
    ансов
    0.08
    NASA
    0.08
    ся
    0.07
    。”
    0.07
    对此
    0.07
    ー�
    0.07
    ётся
    0.07
    ä
    0.07
    Split
    0.07
     NASA
    0.07
    Activations Density 0.199%

    No Known Activations