© 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. 23-RESID-POST-AA
    11. 51689
    Prev
    Next
    INDEX
    Explanations

    Opening parenthesis

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izo
    -0.08
     produkt
    -0.08
     françaises
    -0.08
     जै
    -0.08
     मुख्य
    -0.08
     anvi
    -0.08
     magyar
    -0.08
    ijski
    -0.08
    intval
    -0.08
    (slot
    -0.07
    POSITIVE LOGITS
     px
    0.13
    px
    0.13
     ux
    0.13
    Xp
    0.12
    (px
    0.12
     xc
    0.12
    Px
    0.12
    Xa
    0.12
     Px
    0.12
     xa
    0.11
    Activations Density 0.059%

    No Known Activations