© 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. 75648
    Prev
    Next
    INDEX
    Explanations

    square roots and exponents

    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
     Sinn
    -0.09
     Kata
    -0.08
    ivirus
    -0.07
     mmetụta
    -0.07
     pho
    -0.07
     emprego
    -0.07
    mme
    -0.07
    vimento
    -0.07
    isbn
    -0.07
     Petsc
    -0.07
    POSITIVE LOGITS
    -rate
    0.07
    quarter
    0.07
    منة
    0.07
    rozen
    0.07
    reater
    0.07
    -quarter
    0.07
     liable
    0.07
    trica
    0.07
     п
    0.07
    reat
    0.07
    Activations Density 0.065%

    No Known Activations