© 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. 19021
    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     processes
    -0.09
    일부터
    -0.09
     którzy
    -0.08
     Which
    -0.08
     dy't
    -0.08
     обработки
    -0.08
     Processes
    -0.08
     Zwecke
    -0.08
     które
    -0.08
     kteří
    -0.08
    POSITIVE LOGITS
    _{
    0.13
    _{\
    0.12
    _(
    0.10
    _COM
    0.09
    _\
    0.09
    _[
    0.09
    _LCD
    0.08
    _$
    0.08
     بـ
    0.07
    Central
    0.07
    Activations Density 0.001%

    No Known Activations