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. 106051
    Prev
    Next
    INDEX
    Explanations

    Overhearing conversations

    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
     morphology
    -0.08
     Bildern
    -0.08
     thumbnails
    -0.08
     images
    -0.08
     roller
    -0.08
     sunscreen
    -0.07
    态
    -0.07
     randonnée
    -0.07
    owitz
    -0.07
     trasc
    -0.07
    POSITIVE LOGITS
     разговор
    0.12
     conversaciones
    0.11
     overhe
    0.11
     spoken
    0.10
     gesprekken
    0.10
     reuniones
    0.10
     conversations
    0.10
     듣
    0.10
     কথ
    0.09
     разгов
    0.09
    Activations Density 0.013%

    No Known Activations