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. 101661
    Prev
    Next
    INDEX
    Explanations

    combinatorics and repetition

    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
     expecting
    -0.08
     Pupp
    -0.08
     EXPECT
    -0.08
    EXPECT
    -0.08
    _writer
    -0.08
    Expect
    -0.08
     Magdal
    -0.07
    期待
    -0.07
    .Expected
    -0.07
     Gecko
    -0.07
    POSITIVE LOGITS
     ரச
    0.09
     adulter
    0.08
     хим
    0.08
    feat
    0.08
     spectroscopy
    0.08
    obsolete
    0.08
    许可证
    0.08
     國
    0.08
    -many
    0.08
     contaminants
    0.08
    Activations Density 0.020%

    No Known Activations