© 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. 23-RESID-POST-AA
    11. 48216
    Prev
    Next
    INDEX
    Explanations

    .

    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
    tr
    -0.08
    tration
    -0.08
     T
    -0.08
     കമ്മ
    -0.07
     ком
    -0.07
     committee
    -0.07
    vé
    -0.07
     dlatego
    -0.07
    db
    -0.07
     TR
    -0.07
    POSITIVE LOGITS
    Imper
    0.08
    \Console
    0.08
    Sku
    0.08
     Shakespeare
    0.07
    IVAL
    0.07
     Christopher
    0.07
    .Im
    0.07
    _range
    0.07
    ,N
    0.07
    Cri
    0.07
    Activations Density 0.016%

    No Known Activations