© 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. 75706
    Prev
    Next
    INDEX
    Explanations

    roll

    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
     tú
    -0.09
     medd
    -0.08
     CWE
    -0.08
    oleon
    -0.08
     peng
    -0.08
     Tú
    -0.08
    poral
    -0.07
     Bets
    -0.07
     לב
    -0.07
     cair
    -0.07
    POSITIVE LOGITS
    yez
    0.08
     sti
    0.07
    য়ে
    0.07
    rig
    0.07
    BUR
    0.07
    �
    0.07
    LD
    0.07
     &:
    0.07
    애
    0.07
    Fel
    0.07
    Activations Density 0.022%

    No Known Activations