© 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. 11-RESID-POST-AA
    11. 114168
    Prev
    Next
    INDEX
    Explanations

    completion or repair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tf
    -0.08
     evidence
    -0.08
     thrift
    -0.07
     kurt
    -0.07
     néanmoins
    -0.07
     acessar
    -0.07
    ursal
    -0.07
     �
    -0.07
     trend
    -0.07
    awk
    -0.07
    POSITIVE LOGITS
    Atom
    0.09
     atom
    0.08
     theirs
    0.08
    atom
    0.07
    \Type
    0.07
    <Data
    0.07
     vel
    0.07
    _atom
    0.07
    _dialog
    0.07
     diá
    0.07
    Activations Density 0.116%

    No Known Activations