© 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. 79310
    Prev
    Next
    INDEX
    Explanations

    Dialogue and descriptions

    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
    .Close
    -0.08
     അടുത്ത
    -0.07
    .Resume
    -0.07
     Test
    -0.07
    �
    -0.07
    -↵
    -0.07
     sovereign
    -0.07
     �
    -0.07
     Или
    -0.07
     enem
    -0.07
    POSITIVE LOGITS
    ిపోయ
    0.10
    oneka
    0.09
     دوا
    0.08
    schuld
    0.08
    idikan
    0.08
     बल्कि
    0.08
     selalu
    0.07
     INVENT
    0.07
     Stuff
    0.07
    iap
    0.07
    Activations Density 0.000%

    No Known Activations