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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 56002
    Prev
    Next
    INDEX
    Explanations

    machine

    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
    ifice
    -0.08
     विच
    -0.08
    py
    -0.07
    jw
    -0.07
     सें
    -0.07
     Integrity
    -0.07
    param
    -0.07
     wa
    -0.07
     Pipe
    -0.07
    flate
    -0.07
    POSITIVE LOGITS
     času
    0.09
    ον
    0.08
    (machine
    0.08
    懂
    0.08
    êtres
    0.07
     gelernt
    0.07
     inteligência
    0.07
    .fre
    0.07
     astonishing
    0.07
     machine
    0.07
    Activations Density 0.003%

    No Known Activations