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. 54390
    Prev
    Next
    INDEX
    Explanations

    Code snippets, messages

    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
    :?
    -0.08
     sang
    -0.08
    -0.08
     hän
    -0.08
     garner
    -0.08
     zao
    -0.07
    傷
    -0.07
     했다
    -0.07
     distort
    -0.07
     폭
    -0.07
    POSITIVE LOGITS
    !</
    0.09
     Lorem
    0.09
     HERE
    0.09
    !";↵
    0.08
    Lorem
    0.08
    ...</
    0.08
     blah
    0.08
     hereby
    0.08
     NYC
    0.08
    ...",
    0.08
    Activations Density 0.011%

    No Known Activations