© 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. 11-RESID-POST-AA
    11. 24852
    Prev
    Next
    INDEX
    Explanations

    Math expressions

    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
     subjects
    -0.07
    Air
    -0.07
    _air
    -0.07
    沉
    -0.07
    -air
    -0.07
     неск
    -0.07
     સમ
    -0.07
     Air
    -0.07
     UPDATED
    -0.06
     tor
    -0.06
    POSITIVE LOGITS
    ego
    0.08
     Aby
    0.08
    Pun
    0.08
     abra
    0.08
     boda
    0.08
    496
    0.07
     medal
    0.07
    ضان
    0.07
    vb
    0.07
     sopa
    0.07
    Activations Density 0.203%

    No Known Activations