© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 143
    Prev
    Next
    INDEX
    Explanations

    Bitwise operators

    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
     говоря
    -0.08
     говорить
    -0.08
     Coca
    -0.07
    estaan
    -0.07
    терес
    -0.07
    ahren
    -0.07
     прекращ
    -0.07
    esson
    -0.07
    (action
    -0.07
     action
    -0.07
    POSITIVE LOGITS
    mapper
    0.09
     enumerate
    0.09
     sift
    0.08
    Desired
    0.08
     Sparse
    0.08
    Overlap
    0.08
     yako
    0.08
    Leaves
    0.08
    Atoms
    0.08
    ėtų
    0.08
    Activations Density 0.001%

    No Known Activations