© 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. 51476
    Prev
    Next
    INDEX
    Explanations

    say "the ending -jections"

    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
     tank
    -0.09
    allist
    -0.08
     tanks
    -0.08
     tanque
    -0.08
     zog
    -0.08
    assion
    -0.07
    ต้น
    -0.07
    ording
    -0.07
    .Num
    -0.07
     Tank
    -0.07
    POSITIVE LOGITS
    jections
    0.20
    jection
    0.17
    yección
    0.16
    jected
    0.13
    JECTION
    0.13
    젝
    0.13
     forma
    0.12
    gn
    0.12
    ye
    0.12
     projections
    0.11
    Activations Density 0.003%

    No Known Activations