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. 58165
    Prev
    Next
    INDEX
    Explanations

    to/then sequences

    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
     sums
    -0.09
     medd
    -0.08
     classroom
    -0.08
    .Helper
    -0.08
    百科
    -0.08
    .helper
    -0.07
    理解
    -0.07
     '+
    -0.07
     believers
    -0.07
     Op
    -0.07
    POSITIVE LOGITS
     clockwise
    0.10
    Sequence
    0.09
    quence
    0.08
     followed
    0.08
     이어
    0.08
     sequence
    0.08
    கு
    0.08
    -[#
    0.08
     переход
    0.08
     sequência
    0.08
    Activations Density 0.034%

    No Known Activations