© 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. 19057
    Prev
    Next
    INDEX
    Explanations

    since

    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
    ïs
    -0.09
    โดย
    -0.08
    ush
    -0.08
    กับ
    -0.08
    with
    -0.08
     (§
    -0.08
    ized
    -0.08
    iske
    -0.08
    ushed
    -0.08
    derived
    -0.08
    POSITIVE LOGITS
     τότε
    0.18
     inception
    0.17
     então
    0.15
     then
    0.15
     entonces
    0.15
     allora
    0.14
     akkor
    0.14
    then
    0.13
     وقوع
    0.13
     infancy
    0.12
    Activations Density 0.011%

    No Known Activations