© 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. 70805
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
     hippoc
    -0.09
    �
    -0.09
     anatom
    -0.08
     descendant
    -0.08
     veteran
    -0.08
    Ancestor
    -0.08
     확보
    -0.08
     slept
    -0.08
     ankle
    -0.08
     ancestors
    -0.08
    POSITIVE LOGITS
     chimiques
    0.16
     хим
    0.15
     kinetics
    0.15
     chemical
    0.15
     Chemical
    0.15
     الكيمي
    0.14
     chemicals
    0.14
    chemical
    0.14
     chemistry
    0.14
     chemically
    0.14
    Activations Density 0.035%

    No Known Activations