© 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. 70261
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     compromising
    -0.09
     курс
    -0.08
    .movie
    -0.08
    .exists
    -0.08
    404
    -0.08
     Diskussion
    -0.07
     discussie
    -0.07
     жар
    -0.07
     фильм
    -0.07
     ព
    -0.07
    POSITIVE LOGITS
     elector
    0.08
    Subtype
    0.07
     Versch
    0.07
     vall
    0.07
     appropriate
    0.07
     ulo
    0.07
     adaptation
    0.07
     Dann
    0.07
     darm
    0.07
     diesmal
    0.07
    Activations Density 0.042%

    No Known Activations