Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77537
    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
    ષ્ણ
    -0.08
     поверхности
    -0.07
     PR
    -0.07
    િયાન
    -0.07
    પણ
    -0.07
    ತನ
    -0.07
    ём
    -0.07
     Franklin
    -0.07
    িট
    -0.07
     Bren
    -0.07
    POSITIVE LOGITS
     स्वागत
    0.10
    Soon
    0.09
     Curtains
    0.09
     인해
    0.09
     backstage
    0.09
     അട
    0.08
     സ്വാഗത
    0.08
    -warning
    0.08
    Backdrop
    0.08
     تدري
    0.08
    Activations Density 0.045%

    No Known Activations