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

    Neuronpedia

    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. 3-RESID-POST-AA
    11. 13390
    Prev
    Next
    INDEX
    Explanations

    Λ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Closable
    -0.09
    文本
    -0.08
     sideways
    -0.08
    ują
    -0.07
    多
    -0.07
    ordin
    -0.07
    ક્ષા
    -0.07
     razon
    -0.07
    .forward
    -0.07
    สะ
    -0.07
    POSITIVE LOGITS
     pilot
    0.08
    Pilot
    0.08
     eb
    0.08
    thora
    0.08
    pilot
    0.08
    ைப்பட
    0.07
     Pilot
    0.07
     कु�
    0.07
    413
    0.07
     limitation
    0.07
    Activations Density 0.031%

    No Known Activations