© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18407
    Prev
    Next
    INDEX
    Explanations

    Period

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     లేదా
    -0.13
     અથવા
    -0.13
     hoặc
    -0.12
     or
    -0.12
     किंवा
    -0.12
     أو
    -0.12
     یا
    -0.12
    或
    -0.12
     또는
    -0.11
    或者
    -0.11
    POSITIVE LOGITS
    I'll
    0.15
     I'll
    0.14
    <|end|>
    0.13
    ----↵↵
    0.12
    Since
    0.12
    ------↵↵
    0.11
    ********************************
    0.11
    ---↵↵
    0.11
    -----↵↵
    0.11
    ---------↵↵
    0.11
    Activations Density 0.085%

    No Known Activations