© 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. 110273
    Prev
    Next
    INDEX
    Explanations

    prepositions/conjunctions

    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
    ineno
    -0.08
     capped
    -0.08
     drained
    -0.08
    .VK
    -0.08
     accommodated
    -0.08
     drains
    -0.08
     лет
    -0.08
    ’ir
    -0.08
     Byzant
    -0.08
     dissolved
    -0.07
    POSITIVE LOGITS
    Origin
    0.08
    Lorem
    0.08
    Egg
    0.08
    ================
    0.08
     Origin
    0.08
    Subtitle
    0.07
    --------------------------------
    0.07
    _visible
    0.07
     FL
    0.07
    ambula
    0.07
    Activations Density 0.226%

    No Known Activations