© 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. 65594
    Prev
    Next
    INDEX
    Explanations

    math intervals and inequalities

    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
     sint
    -0.09
    Sint
    -0.08
     maggior
    -0.08
     Szen
    -0.08
     SIDE
    -0.08
     λι
    -0.08
     राहत
    -0.08
    止
    -0.08
     ван
    -0.08
     grues
    -0.07
    POSITIVE LOGITS
    #set
    0.09
     subscriber
    0.08
    >#
    0.08
    —but
    0.08
    \M
    0.08
    #w
    0.08
    #error
    0.08
    ets
    0.08
    번째
    0.07
    ope
    0.07
    Activations Density 0.092%

    No Known Activations