© 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. 18475
    Prev
    Next
    INDEX
    Explanations

    geometry and math

    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
    Название
    -0.08
    --------------------------------
    -0.08
    ————————
    -0.08
    dddd
    -0.08
    rrrr
    -0.08
    оми
    -0.08
     XXXXX
    -0.07
    cccc
    -0.07
     XXXX
    -0.07
    ________________________________
    -0.07
    POSITIVE LOGITS
     AC
    0.09
     ac
    0.08
     zinaz
    0.08
     ibang
    0.08
     jiné
    0.08
    acan
    0.08
    AC
    0.08
     osią
    0.08
    -la
    0.08
     akad
    0.08
    Activations Density 0.034%

    No Known Activations