© 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. 18895
    Prev
    Next
    INDEX
    Explanations

    Children

    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
    neden
    -0.10
     nifty
    -0.09
    ు
    -0.09
    chrift
    -0.09
    feiço
    -0.09
     exercitation
    -0.09
    ↵
↵//
    -0.09
    möglichkeiten
    -0.09
    oine
    -0.09
    ição
    -0.09
    POSITIVE LOGITS
    -anak
    0.16
    ’s
    0.14
    rens
    0.13
    riages
    0.11
    `s
    0.10
    們
    0.10
    /ad
    0.10
    ‘s
    0.10
    (children
    0.10
    "s
    0.10
    Activations Density 0.043%

    No Known Activations