© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18711
    Prev
    Next
    INDEX
    Explanations

    say "to"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kod
    -0.07
    rocks
    -0.07
    _setup
    -0.07
    iselwa
    -0.06
     Кто
    -0.06
     Understanding
    -0.06
     Kur
    -0.06
    ifl
    -0.06
     כיצד
    -0.06
     Verständnis
    -0.06
    POSITIVE LOGITS
     hacerlo
    0.20
     fazê
    0.18
     it
    0.17
     ذلك
    0.16
     בכך
    0.15
     ello
    0.15
     thereto
    0.14
     그렇게
    0.14
     izany
    0.14
     doing
    0.14
    Activations Density 0.038%

    No Known Activations