© 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. 22249
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ilon
    -0.08
     shovel
    -0.08
    ṣẹ
    -0.08
    াত
    -0.07
    274
    -0.07
    ারে
    -0.07
     wound
    -0.07
     opzichte
    -0.07
     לו
    -0.07
     Pueblo
    -0.07
    POSITIVE LOGITS
    setzungen
    0.18
    setzung
    0.16
    stellingen
    0.16
    /object
    0.12
    -oriented
    0.12
     हासिल
    0.12
    -setting
    0.11
    Reached
    0.11
    stelling
    0.11
    مند
    0.11
    Activations Density 0.039%

    No Known Activations