© 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. 95877
    Prev
    Next
    INDEX
    Explanations

    not

    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
     Nah
    -0.07
    ्सा
    -0.07
     meg
    -0.07
     consumer
    -0.07
     realistically
    -0.07
     صحت
    -0.07
     സൗ
    -0.07
    �
    -0.07
     част
    -0.07
     retrospective
    -0.07
    POSITIVE LOGITS
    Emission
    0.08
    Occupied
    0.08
     Turner
    0.08
    Firestore
    0.08
     Escolar
    0.08
     hur
    0.08
    occupied
    0.07
    REP
    0.07
    بری
    0.07
     Medal
    0.07
    Activations Density 0.029%

    No Known Activations