© 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. 21651
    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
     originally
    -0.10
     initially
    -0.09
     oorspronk
    -0.09
     ursprünglich
    -0.08
    anggan
    -0.08
     originalmente
    -0.08
     letzten
    -0.08
     laatst
    -0.08
    alagi
    -0.08
     gwy
    -0.08
    POSITIVE LOGITS
     उपकरण
    0.08
     त्यांच्या
    0.08
     निर्णय
    0.08
     समुदाय
    0.08
    2
    0.08
     招
    0.07
     motivation
    0.07
     motiv
    0.07
     "
    0.07
    3
    0.07
    Activations Density 0.000%

    No Known Activations