© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 65003
    Prev
    Next
    INDEX
    Explanations

    --

    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
    HING
    -0.08
    fear
    -0.08
     villas
    -0.07
    pread
    -0.07
     ישראל
    -0.07
    virus
    -0.07
    zech
    -0.07
     DVR
    -0.07
     bother
    -0.07
    iede
    -0.07
    POSITIVE LOGITS
     "?
    0.08
     entendido
    0.08
    ути
    0.07
     κο
    0.07
    0.07
    /kg
    0.07
     metr
    0.07
    .fb
    0.07
     versteht
    0.07
     понять
    0.07
    Activations Density 0.002%
    No Known Activations