© 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 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. 69909
    Prev
    Next
    INDEX
    Explanations

    like

    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
     населения
    -0.11
     stell
    -0.09
     בלבד
    -0.08
    _prof
    -0.08
    CTS
    -0.08
     насел
    -0.08
     populace
    -0.08
    ossier
    -0.07
     יוצ
    -0.07
     örg
    -0.07
    POSITIVE LOGITS
     precisely
    0.08
     old
    0.07
     authentic
    0.07
     firsthand
    0.07
     instinct
    0.07
     footsteps
    0.07
    니까
    0.07
     حض
    0.07
    authenticate
    0.07
     hindsight
    0.07
    Activations Density 0.028%

    No Known Activations