© 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. 64220
    Prev
    Next
    INDEX
    Explanations

    Calculations and formulas

    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
     stereo
    -0.09
     Laser
    -0.09
     magician
    -0.09
     myth
    -0.08
     queer
    -0.08
     Tunes
    -0.08
     tuner
    -0.08
     diffuser
    -0.08
     Fairy
    -0.08
    -place
    -0.08
    POSITIVE LOGITS
     EBITDA
    0.16
    income
    0.15
     EBIT
    0.15
     income
    0.15
    Income
    0.15
    _income
    0.15
     Income
    0.15
    Revenue
    0.14
    指标
    0.14
     Earnings
    0.14
    Activations Density 0.026%

    No Known Activations