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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49738
    Prev
    Next
    INDEX
    Explanations

    Har

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    амо
    -0.08
    аметр
    -0.08
    φαν
    -0.07
     aneur
    -0.07
    tay
    -0.07
    란
    -0.07
    (combo
    -0.07
     //~
    -0.07
    Atlanta
    -0.07
    퓨터
    -0.07
    POSITIVE LOGITS
    assment
    0.18
     Har
    0.17
    Har
    0.16
     har
    0.14
     HAR
    0.13
    har
    0.13
    HAR
    0.13
    èlement
    0.12
     Хар
    0.12
    rowing
    0.11
    Activations Density 0.028%

    No Known Activations