© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 110114
    Prev
    Next
    INDEX
    Explanations

    square wave

    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
     hashtags
    -0.08
     locaux
    -0.08
     Eles
    -0.07
    ained
    -0.07
    措
    -0.07
     inpatient
    -0.07
     Bem
    -0.07
    ASH
    -0.07
    地点
    -0.07
    PIRE
    -0.07
    POSITIVE LOGITS
     waveform
    0.14
     sinus
    0.12
    _voltage
    0.11
     sine
    0.11
     voltage
    0.10
    周期
    0.10
    _pwm
    0.09
    Voltage
    0.09
     shape
    0.09
     Voltage
    0.09
    Activations Density 0.006%

    No Known Activations