© 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. 18723
    Prev
    Next
    INDEX
    Explanations

    but

    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
     কোনও
    -0.08
    ustra
    -0.08
     કરતા
    -0.08
    -for
    -0.08
     intelig
    -0.08
    ith
    -0.08
    utico
    -0.07
    อย่าง
    -0.07
     Erkennt
    -0.07
     능
    -0.07
    POSITIVE LOGITS
     want
    0.15
     vouloir
    0.11
     wonder
    0.11
     wanting
    0.11
     хочется
    0.11
     suspect
    0.11
    觉得
    0.11
     wondered
    0.10
     wondering
    0.10
     싶은
    0.10
    Activations Density 0.009%

    No Known Activations