© 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. 71315
    Prev
    Next
    INDEX
    Explanations

    Constraint

    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
     θε
    -0.08
     DOS
    -0.08
    ícia
    -0.08
     nag
    -0.07
     듣
    -0.07
     призн
    -0.07
     structure
    -0.07
     dividends
    -0.07
     anthology
    -0.07
     rog
    -0.07
    POSITIVE LOGITS
    .Constraint
    0.10
    decorate
    0.10
    .constraint
    0.10
     NSLayout
    0.10
    Layout
    0.09
    .optimize
    0.09
    Dependency
    0.09
    Constraint
    0.08
    mph
    0.08
    Constraints
    0.08
    Activations Density 0.002%

    No Known Activations