© 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. 111363
    Prev
    Next
    INDEX
    Explanations

    Fictional characters

    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
     информа
    -0.08
     ум
    -0.08
     знач
    -0.08
     conscientious
    -0.08
     свой
    -0.08
    ikipedia
    -0.08
     законодатель
    -0.08
     término
    -0.07
     shaded
    -0.07
    итут
    -0.07
    POSITIVE LOGITS
     Dare
    0.09
    addons
    0.09
     immort
    0.08
     dear
    0.08
     ועל
    0.08
     dando
    0.08
    और
    0.08
     Emmanuel
    0.08
    -proof
    0.08
    ليس
    0.08
    Activations Density 0.051%

    No Known Activations