© 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. 70680
    Prev
    Next
    INDEX
    Explanations

    SERS

    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
     wage
    -0.10
    ANGUAGE
    -0.10
     freezer
    -0.09
     Wage
    -0.09
     Catherine
    -0.09
    Throttle
    -0.09
     pneumatic
    -0.08
    Wheel
    -0.08
     commuting
    -0.08
     waking
    -0.08
    POSITIVE LOGITS
     plas
    0.10
     nanoparticles
    0.09
     resonance
    0.09
    .geo
    0.09
     amplification
    0.08
     influencer
    0.08
     gold
    0.08
     nanos
    0.08
     plasm
    0.08
     अवसर
    0.08
    Activations Density 0.003%

    No Known Activations