© 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. 18511
    Prev
    Next
    INDEX
    Explanations

    file formats and signatures

    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
     mute
    -0.09
     ಪರಿ�
    -0.08
     தீர
    -0.08
     шеш
    -0.08
     CSS
    -0.08
    ’ancien
    -0.08
     beschlossen
    -0.08
     solusi
    -0.08
     vicious
    -0.08
     פתר
    -0.08
    POSITIVE LOGITS
    \xd
    0.14
    \xb
    0.13
    \x
    0.13
    _SIGNATURE
    0.12
    \xf
    0.11
    \xc
    0.11
    _MAGIC
    0.11
    \xe
    0.11
    _magic
    0.11
    ÿ
    0.11
    Activations Density 0.001%

    No Known Activations