© 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. 26134
    Prev
    Next
    INDEX
    Explanations

    potentiometers

    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
     Te
    -0.08
    ments
    -0.08
    Te
    -0.07
     Franz
    -0.07
     voices
    -0.07
     Dolores
    -0.07
     אנחנו
    -0.07
    ศก
    -0.07
     Datenschutz
    -0.07
     mayroon
    -0.07
    POSITIVE LOGITS
     bound
    0.09
    �
    0.07
    了承
    0.07
    inare
    0.07
     lazım
    0.07
     wille
    0.07
    滿
    0.07
    (bound
    0.07
     phục
    0.07
     nero
    0.07
    Activations Density 0.000%

    No Known Activations