© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25049
    Prev
    Next
    INDEX
    Explanations

    electrochemical cells

    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
    uições
    -0.09
    ळ
    -0.08
    fól
    -0.08
    τ
    -0.08
    �ে
    -0.08
    ằng
    -0.08
    Γ
    -0.08
    mey
    -0.07
    veux
    -0.07
    əş
    -0.07
    POSITIVE LOGITS
     Fleming
    0.08
    _FIND
    0.08
    Calculator
    0.08
     emf
    0.08
     weakest
    0.08
     unequal
    0.08
     weak
    0.08
     Weak
    0.08
     weakness
    0.07
    弱
    0.07
    Activations Density 0.005%

    No Known Activations