© 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. 11-RESID-POST-AA
    11. 110352
    Prev
    Next
    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brazilian
    -0.07
     Nip
    -0.07
    unti
    -0.07
     pecc
    -0.07
     infatti
    -0.07
     movil
    -0.07
     зат
    -0.07
     NPC
    -0.07
     اختصاص
    -0.07
    unp
    -0.06
    POSITIVE LOGITS
    (|
    0.09
    iesel
    0.08
     juniors
    0.08
    ...,
    0.08
     invites
    0.08
    die
    0.08
    _CB
    0.07
    awl
    0.07
    Users
    0.07
    arks
    0.07
    Activations Density 0.165%

    No Known Activations