© 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 EvalsExportsAPI 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. 49643
    Prev
    Next
    INDEX
    Explanations

    De

    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
    an
    -0.10
    vi
    -0.09
    letes
    -0.09
    e
    -0.09
    i
    -0.08
    ar
    -0.08
    іка
    -0.08
    us
    -0.08
    er
    -0.08
    arlan
    -0.08
    POSITIVE LOGITS
    crease
    0.13
    viation
    0.12
    graduate
    0.11
    letion
    0.11
    gradation
    0.11
    clarations
    0.11
    creasing
    0.10
    ps
    0.10
    creased
    0.10
    crypt
    0.09
    Activations Density 0.005%

    No Known Activations