© 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. 70024
    Prev
    Next
    INDEX
    Explanations

    conic polar equations

    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
     incênd
    -0.09
     who
    -0.08
    .bus
    -0.08
     einge
    -0.08
     mitochondrial
    -0.08
     infrastrukt
    -0.07
     bust
    -0.07
     neuronal
    -0.07
     camar
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     Tooth
    0.08
    alq
    0.08
     Religious
    0.08
    ovit
    0.08
     Refuge
    0.07
     conquest
    0.07
    <Value
    0.07
     Peach
    0.07
     Raleigh
    0.07
    $_['
    0.07
    Activations Density 0.018%

    No Known Activations