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. 119308
    Prev
    Next
    INDEX
    Explanations

    rank or position

    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
     governments
    -0.10
     what
    -0.08
     terp
    -0.08
     Ty
    -0.07
    قق
    -0.07
     उत्त
    -0.07
     filters
    -0.07
     ty
    -0.07
    FUL
    -0.07
    .filters
    -0.07
    POSITIVE LOGITS
     posição
    0.12
    positie
    0.12
     posición
    0.11
     positie
    0.11
    	position
    0.11
     пози
    0.11
    position
    0.11
     नंबर
    0.11
     ಸ್ಥಾನ
    0.11
     номер
    0.11
    Activations Density 0.015%

    No Known Activations