© 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. 114347
    Prev
    Next
    INDEX
    Explanations

    station

    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
     teeth
    -0.08
     خطاب
    -0.08
     αρχ
    -0.08
     LUT
    -0.08
     आरोप
    -0.07
    odus
    -0.07
     grin
    -0.07
    Ạ
    -0.07
     सीधे
    -0.07
    .targets
    -0.07
    POSITIVE LOGITS
     shelter
    0.08
     enrichment
    0.08
    Human
    0.08
    Ground
    0.08
    Science
    0.08
     NOAA
    0.08
     observa
    0.08
    Singer
    0.08
    _alive
    0.08
     Webcam
    0.07
    Activations Density 0.003%

    No Known Activations