© 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. 18859
    Prev
    Next
    INDEX
    Explanations

    python

    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
    ième
    -0.10
    denes
    -0.10
    raí
    -0.10
    teous
    -0.10
    atá
    -0.10
    numerusform
    -0.10
     dunha
    -0.10
    ,’
    -0.10
    สดงความคิดเห็น
    -0.10
    ández
    -0.10
    POSITIVE LOGITS
    3
    0.23
    2
    0.17
    4
    0.16
    5
    0.15
    6
    0.15
    8
    0.14
    7
    0.14
    1
    0.14
    32
    0.13
    9
    0.13
    Activations Density 0.001%

    No Known Activations