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. 65684
    Prev
    Next
    INDEX
    Explanations

    language model cutoff dates

    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
     Protestant
    -0.08
     enam
    -0.08
     bipartisan
    -0.07
    incode
    -0.07
    -0.07
    Mot
    -0.07
     efficient
    -0.07
    ucao
    -0.07
    igned
    -0.07
    wm
    -0.07
    POSITIVE LOGITS
    .Tree
    0.11
     septiembre
    0.09
    纳
    0.08
     cutoff
    0.08
     setembro
    0.08
     সেপ্টেম্বর
    0.08
     septembre
    0.08
     tree
    0.08
    .tree
    0.08
     árvore
    0.08
    Activations Density 0.075%

    No Known Activations