© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 102600
    Prev
    Next
    INDEX
    Explanations

    Code or technical documentation

    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
     ಎರಡ
    -0.08
    ;complex
    -0.08
     SAME
    -0.08
    _ELEMENT
    -0.08
    _Config
    -0.07
    ––––
    -0.07
     הלא
    -0.07
     VERY
    -0.07
     ALSO
    -0.07
     again
    -0.07
    POSITIVE LOGITS
    нікі
    0.09
    such
    0.09
    奷
    0.09
    �
    0.08
    цы
    0.08
     cyo
    0.08
     tels
    0.08
    ㅠ
    0.08
    ымы
    0.08
    �
    0.08
    Activations Density 0.012%

    No Known Activations