© 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. 19130
    Prev
    Next
    INDEX
    Explanations

    Photographic style and camera details

    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
    алее
    -0.11
    /random
    -0.10
    /function
    -0.10
    Но
    -0.09
     Außerdem
    -0.09
    ,and
    -0.09
    ,but
    -0.09
     зато
    -0.09
    然后
    -0.09
    ...).
    -0.09
    POSITIVE LOGITS
     a
    0.13
     high
    0.11
     United
    0.10
     "
    0.10
    0.10
     twilight
    0.10
     High
    0.10
     two
    0.09
    _HIGH
    0.09
     the
    0.09
    Activations Density 0.001%

    No Known Activations