© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26105
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     জন
    -0.07
    -0.07
     hobby
    -0.07
    によ
    -0.07
    数量
    -0.07
     হও
    -0.07
    -0.07
     গেলে
    -0.07
     মূল্য
    -0.07
     existente
    -0.07
    POSITIVE LOGITS
    @Retention
    0.09
    PECIAL
    0.09
    -defense
    0.09
     бонус
    0.09
     cavalry
    0.09
     Detta
    0.09
     बोनस
    0.09
     uncont
    0.08
     जंगल
    0.08
     beware
    0.08
    Activations Density 0.011%

    No Known Activations