© 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. 51685
    Prev
    Next
    INDEX
    Explanations

    Bank balance/statements

    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
    weighted
    -0.08
     Versand
    -0.08
    weapon
    -0.08
     игре
    -0.08
     receta
    -0.08
    riors
    -0.08
     hotels
    -0.08
    _weapon
    -0.08
    subset
    -0.08
    docker
    -0.08
    POSITIVE LOGITS
     balance
    0.23
    _balance
    0.21
     statement
    0.20
    .balance
    0.20
    余额
    0.20
    Balance
    0.20
     saldo
    0.20
     Balance
    0.19
    (balance
    0.19
    balance
    0.18
    Activations Density 0.020%

    No Known Activations