© 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. 25177
    Prev
    Next
    INDEX
    Explanations

    with

    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
     unlucky
    -0.08
     nala
    -0.08
     kandidat
    -0.08
     wets
    -0.08
     Champion
    -0.08
     despre
    -0.07
     pene
    -0.07
     appena
    -0.07
    েরা
    -0.07
     detaine
    -0.07
    POSITIVE LOGITS
    Sk
    0.08
    jmp
    0.07
    ffi
    0.07
    sk
    0.07
    天
    0.07
     गण
    0.07
    ùi
    0.07
    achievement
    0.07
     calculus
    0.07
    үр
    0.07
    Activations Density 0.000%

    No Known Activations