© 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. 18370
    Prev
    Next
    INDEX
    Explanations

    person

    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
    $new
    -0.07
     tsim
    -0.07
     رہے
    -0.07
    uhe
    -0.07
    -0.07
    &a
    -0.07
    کتا
    -0.07
     artillery
    -0.07
    $output
    -0.07
    (hidden
    -0.07
    POSITIVE LOGITS
     persönlich
    0.28
     лично
    0.27
     persoonlijk
    0.25
     személy
    0.24
     pessoal
    0.24
     presencial
    0.23
     personalmente
    0.23
     personally
    0.22
     person
    0.21
     شخص
    0.21
    Activations Density 0.048%
    No Known Activations